SlideShare a Scribd company logo
1 of 185
Download to read offline
Deep Learning
Chainer
34 2017
Researcher @ Preferred Networks
1
Agenda
•
•
•
•
•
•
• Chainer
• numpy Chainer
•
•
• GAN
•
•
2
•
•
• 2010
• 2012
• 2013 - 2014 UC Berkeley (Visiting Student Researcher)
• 2015
• 2016 @ "Semantic
Segmentation for Aerial Imagery with Convolutional
Neural Network"
• 2016.9 Facebook, Inc.
• 2016.9 Preferred Networks, Inc.
3
• Preferred Networks
• PFN
• 106 8
•
• FANUC Toyota NTT
• We are hiring!
4
PFN
AutomotiveHumanoid	 Robot
Consumer Industrial
Cloud
Device
Photo
Game
Text
Speech
Infrastructure
Factory
Robot
Automotive
Healthcare
Smart	City
Industry4.0
Industrial	IoT
5
•
• Chainer Define-by-Run
• Chainer
• GAN
• ChaineCV ChainerRL
6
7
8
•
•
fully-connected layer
9
4 3 2 1 0 1 2 3 4
x
1
0
1
2
3
4
y
y = 1/(1 + exp(x))
y = tanh(x)
y = max(0, x)
•
ReLU
•
activation function
Maxout1
, LReLU2
,
PReLU3
, ELU4
, SELU5
, etc.
10
"core idea"
The core idea in deep learning is that we
assume that the data was generated by
the composition of factors or features,
potentially at multiple levels in a hierarchy.
— Ian Goodfellow, Yoshua Bengio, Aaron
Courville, "Deep Learning"
11
.
representation
12
h(1)
= a(1)
(W(1)
x + b(1)
)
h(l)
= a(l)
(W(l)
h(l 1)
+ b(l 1)
)
o = a(o)
(W(o)
h(o)
+ b(o)
)
•
•
•
hidden layer 1
1
1
Kurt Hornik, Maxwell Stinchcombe, Halbert White, "Multilayer
feedforward networks are universal approximators", Neural Networks
(1989)
13
A visual proof that neural nets can compute any function”
http://neuralnetworksanddeeplearning.com/chap4.html
(1)
•
• 1
14
A visual proof that neural nets can compute any function”
http://neuralnetworksanddeeplearning.com/chap4.html
(2)
• 2
•
15
A visual proof that neural nets can compute any function”
http://neuralnetworksanddeeplearning.com/chap4.html
(3)
•
•
•
16
A visual proof that neural nets can compute any function”
http://neuralnetworksanddeeplearning.com/chap4.html
(4)
•
•
17
A visual proof that neural nets can compute any function”
http://neuralnetworksanddeeplearning.com/chap4.html
(5)
•
•
• 4
18
(6)
•
6
•
2
6
“A visual proof that neural nets can compute any function”
http://neuralnetworksanddeeplearning.com/chap4.html
19
(7)
•
• 7
2
7
“A visual proof that neural nets can compute any function”
http://neuralnetworksanddeeplearning.com/chap4.html
20
so many nodes
Replacable?
• 1
•
21
•
•
… 8
• piecewise linear function
9
9
Razvan Pascanu, Guido Montufar, and Yoshua Bengio, "On the number of response regions of deep feed forward
networks with piece-wise linear activations", NIPS (2014)
8
Merrick Furst, James B. Saxe, and Michael Sipser, "Parity, Circuits, and the Polynomial-Time Hierarchy",
Mathematical systems theory (1984)
22
•
training data
•
•
23
•
•
loss function
•
24
•
• softmax
• one-hot
• cross entropy
25
• gradient method
gradient descent
•
• learning rate
•
26
backpropagation
•
•
•
27
•
minibatch
•
An overview of gradient descent
optimization algorithms
28
SGD without momentum
SGD with momentum
*
Stochastic gradient descent (SGD)
Momentum SGD15
15
A. Krizhevsky, I. Sutskever, G. E. Hinton, "ImageNet Classification with
Deep Convolutional Neural Networks", NIPS (2012)
29
Nesterov accelerated gradient (NAG)16
Momentum SGD
RNN
AdaGrad17
AdaDelta18
AdaGrad
RMSProp19
, Adam20
, Eve21
…
30
: sigmoid cross entropy
•
•
31
: sigmoid cross entropy
•
exploding gradients
…↓
•
vanishing gradient
32
33
Greedy layer-wise pre-training10
•
Yoshua Bengio ICML 2009
10
Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle, "Greedy layer-wise
training of deep networks", NIPS (2006)
34
ReLU rectified linear unit 11
• Sigmoid
0
11
Xavier Glorot, Antoine Bordes, and Yoshua Bengio, "Deep Sparse
Rectifier Neural Networks", NIPS Workshop (2010)
35
Dropout12
•
[13] Figure 1 13
13
N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R.
Salakhutdinov, "Dropout: A Simple Way to Prevent Neural Networks from
Overfitting", Journal of Machine Learning Research (2014)
12
G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R.
Salakhutdinov, "Improving neural networks by preventing co-adaptation
of feature detectors", On arxiv (2012)
36
[14]
Residual learning 14
•
•
14
K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image
Recognition", CVPR (2016)
37
38
•
1. forward
Dropout
2. backward
3. autograd
2.
4. optimizer 3.
39
Chainer
Preferred Networks
Python
https://github.com/chainer/chainer
40
Popularity Growth of Chainer
41
Define-and-Run Define-by-Run
Define-and-Run
Define-and-Run Define-by-Run
Define-and-Run
Chainer
•
• Define-and-Run
• Define-by-Run
•
Define-and-Run
42
Define-and-Run Define-by-Run
43
Define-by-Run
•
• Python
• Caffe
prototxt
• recurrent neural
network; RNN for
BPTT backpropagation through time
44
numpy Chainer
45
Variable
Function
Function
Function
Variable Variable
VariableVariable Variable
VariableVariable Variable
(1)
Variable Function
• 2 Variable
Function
• Variable
Function
directed asyclic graph; DAG
• Variable Function
rank
46
rank=0
rank=1
rank=2
Variable
Function
Function
Function
Variable Variable
VariableVariable Variable
VariableVariable Variable
creator
creator
inputs
inputs
inputs
(2)
• backward
• Function Variable
inputs
• Function Variable
Function creator
• Function Variable rank
Function Variable Function
1 rank
47
Chainer
Chainer
48
grad_outputs
.backward(inputs, grad_outputs)
.backward(inputs, grad_outputs)
grad
Function
Function
.backward()
grad
Variable
.inputs
Variable Variable
grad_outputs
.creator.creator
grad_outputs
grad grad grad
VariableVariable Variable
.backward(inputs, grad_outputs)
grad_outputs
grad grad grad
VariableVariable Variable
Function
.inputs
creator
.inputs
=1
creator
(1)
• Define-by-Run
backward Variable
• Variable backward()
Function
backward()
•
inputs
•
grad_outputs
49
(2)
• Variable
Chainer
•
•
grad
50
(3)
• Function backward()
• Function outputs
outputs→creator→outputs
• Function
Function
x, W, b = Variable(init_x), Variable(init_W), Variable(init_b)
y = LinearFunction()(x, W, b) # forward
# ...backward, update ...
y = LinearFunction()(x, W, b) # forward
51
Link
• W, b
Function
• Link
•
params()
52
Chain
•
•
• Link
params() Link
53
Optimizer
• Optimizer setup()
Chain Link update()
• Optimizer
• Chainer state
54
• Linear
ReLUFunction
• ReLU
ReLUFunction
• ReLU (
55
• 2
mean
squared error; MSE
• MSE
ReLU
56
•
: MNIST
• 100 1
forward
• SGD Optimizer
setup()
57
• MNIST scikit-learn
from sklearn.datasets import fetch_mldata
mnist = fetch_mldata('MNIST original', data_home='./')
x, t = mnist['data'] / 255, mnist['target']
t = numpy.array([t == i for i in range(10)]).T
train_x, train_t = x[:60000], t[:60000]
val_x, val_t = x[60000:], t[60000:]
• 1
• 150
58
• 94%
•
http://bit.ly/mini_chainer_mnist
• numpy
Define-by-Run
59
Chainer
60
Trainer (1)
Optimizer
• Trainer
• Chainer Chain
• chainer.optimizer
SGD,
MomentumSGD, NesterovAG, RMSprop,
RMSpropGraves, AdaGrad, AdaDelta,
Adam, etc...
61
Trainer (2)
• Chainer
• MNIST
• Validation
len(val)
62
Trainer (3)
•
• Chainer chainer.functions
chainer.links
• softmax cross entropy
63
Trainer
• Trainer
Optimizer
•
• Trainer Extension
import
import
64
Trainer (1)
• Extension
• snapshot
• LogReport, PrintReport
• validation Evaluator
• PlotReport
• Graphviz dot dump_graph
• ParameterStatistics
•
• Trainer extensions (https://docs.chainer.org/en/stable/reference/extensions.html)
65
Trainer (2)
•
•
• Trainer
• GPU ParallelUpdater, MultiprocessParallelUpdater
MultiprocessIterator
66
GPU
•
• Chainer CuPy GPGPU
• CuPy NCCL NCCL2 GPU
• cuDNN NVIDIA v7 CUDA v9
• fp16
67
CuPy
• CuPy NumPy
NVIDIA CUDA GPU
• NumPy API
NumPy
GPU
•
GPU
• KMeans, Gaussian Mixture Model
Example
CuPy: https://github.com/cupy/cupy
68
69
•
•
• Semantic Segmentation
• Instanse-aware Segmentation
70
horse : 94%
dog : 3%
pig : 2%
cat : 1%
.
.
.
71
R
G
B
72
•
• convolutional layer
• pooling
[A. Krizhevsky, 2016]15
**
15
A. Krizhevsky, I. Sutskever, G. E. Hinton, "ImageNet Classification with
Deep Convolutional Neural Networks", NIPS (2012)
73
• convolutional neural
network; CNN
•
• 1
74
•
•
• stride
• padding
CS231n Convolutional Neural Networks for
Visual Recognition
75
•
•
receptive field
•
CS231n Convolutional Neural
Networks for Visual Recognition
76
77
2012 Toronto Geoffry Hinton
2 10%
28.191
25.77
15.315
11.743
6.656
5.1
3.567 2.991 2.251
ILSVRC	Object	Classification	(Top-5	Error)ImageNet Large Scale Visual
Recognition Challenge
(ILSVRC)
• 1000 1
128 1000
• 2010
• 2011 localization
• 2012 Fine-grained
• 2013 bounding box
• 2015
• 2016
78
AlexNet15
• 2012 ILSVRC
• 224x244 5
3
• LRN (local response normalization) ReLU max
pooling
• AlexNet ImageNet
pre-trained model
• AlexNet pre-trained model
transfer learning
15
A. Krizhevsky, I. Sutskever, G. E. Hinton, "ImageNet Classification with
Deep Convolutional Neural Networks", NIPS (2012)
79
GoogleNet16
• 2014 ILSVRC Inception
ResNet
• Inception
22
• 1x1, 3x3, 5x5
concat
• 1x1
16
C. Szegedy, et. al., "Going Deeper with Convolutions", CVPR (2015)
80
VGG17
• 2014 GoogLeNet ILSVRC 2
• 3x3
1
receptive field 3x3 2
5x5, 3 7x7 receptive field
•
ResNet pre-trained
17
K. Simonyan, A. Zisserman "Very Deep Convolutional Networks for
Large-Scale Image Recognition" arXiv technical report, (2014)
81
ResNet18
• ILSVRC 2015 GoogLeNet 22
152
CIFAR
1502
•
•
18
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
, "Deep Residual Learning for Image Recognition." arXiv:1512.03385
(2015)
82
Wide-ResNet19
• ResNet
" "
ResNet
• Residual block Dropout ratio
30~40%
19
Sergey Zagoruyko, Nikos Komodakis, "Wide Residual Networks", arXiv:
1605.07146 (2016)
83
DenseNet20
• CVPR 2017 Residual
connection 2 ResBlock
•
•
20
Gao Huang, Zhuang Liu, Kilian Q. Weinberger, Laurens van der Maaten,
"Densely Connected Convolutional Networks", CVPR (2017)
84
ResNeXt21
• 2016 ILSVRC 2
•
• cardinality
•
cardinality
21
Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He,
"Aggregated Residual Transformations for Deep Neural Networks", CVPR
(2017)
85
Squeeze-and-Excitation22
• 2017 ILSVRC
• Inception
•
•
squeeze
excitation
22
Jie Hu, Li Shen, Gang Sun, "Squeeze-and-Excitation Networks", arXiv
pre-print: 1709.01507 (2017)
86
- 2017 ILSVRC
Kaggle ImageNet Object
Localization Challenge)
-
- MSCOCO Dataset
- Places Challenge (ADE20K)
- YouTube-8M Video Understanding Challenge
- Cityscapes Dataset
- Mapillary Vistas Datset
- VisualGenome
87
88
Fast R-CNN
Faster R-CNN
Faster/Fast R-CNN/R-CNN23
• R-CNN: region proposals selective
search CNN
resize CNN
SVM
• Fast R-CNN:
RoI Pooling
bounding box bbox regression
• Faster R-CNN: Region proposal network (RPN)
CNN RPN
/ bbox
23
Ren, Shaoqing, et al. "Faster R-CNN: Towards real-time object
detection with region proposal networks." NIPS (2015)
89
You Only Look Once (YOLO)25
•
bounding box
• bounding box
1
end-to-end
• FCN
YOLO9000 CVPR2017
25
Redmon, Joseph, et al. "You only look once: Unified, real-time object
detection." arXiv preprint arXiv:1506.02640 (2015)
90
Single Shot Multibox
Detector (SSD)24
• YOLO Faster R-CNN
•
•
• End-to-end
24
Liu, Wei, et al. "SSD: Single Shot MultiBox Detector." ECCV (2016)
91
Semantic Segmentation
92
Semantic Segmentation
•
•
" "
• Instance-aware
93
(1)
Dilated convolution51
•
•
51
"Multi-Scale Context Aggregation by Dilated Convolutions", ICLR 2016
94
(2)
Multi-scale feature ensemble
•
•
52
52
"Hypercolumns for Object Segmentation and Fine-grained
Localization", CVPR 2015
95
(3)
Conditional random field (CRF)
• CNN refine
(DeepLab53
)
• DeepLab
refine End-to-End
(DPN54
, CRF as RNN55
, Detections and
Superpixels56
)
56
"Higher order conditional random fields in deep neural networks",
ECCV 2016
55
"Conditional random fields as recurrent neural networks", ICCV 2015
54
"Semantic image segmentation via deep parsing network", ICCV 2015
53
"Semantic image segmentation with deep convolutional nets and fully
connected crfs", ICLR 2015
96
(4)
Global average pooling (GAP)
•
• ParseNet57
Global average pooling
FCN
57
"Parsenet: Looking wider to see better", ICLR 2016
97
(1)
Mismatched relationship
•
•
•
• FCN
98
(2)
Confusing Classes
•
• ADE20K
17.6%
58
• FCN
•
58
"Semantic understanding of scenes through the ADE20K dataset",
CVPR 2017
99
(3)
Inconspicuous Classes
•
•
FCN
•
sub-
region
100
•
•
•
101
Fully Convolutional Network26
• Classification
pre-training
1x1
• Deconvolution
• semantic low
level skip connection
26
Jonathan Long and Evan Shelhamer et al., "Fully Convolutional
Networks for Semantic Segmentation", appeared in arxiv on Nov. 14,
2014
102
Deconvolution
• Deconvolution transposed
convolution backward convolution
• Convolution
1. stride
2. -1
3. padding
4. Convolution
• stride
Convolution arithmetic https://github.com/vdumoulin/
conv_arithmetic
103
Global Average Pooling (GAP)59
•
• ResNet receptive field
• GAP
•
59
"Parsenet: Looking wider to see better", ICLR 2016
104
SegNet27
•
• Max pooling
•
0
27
Vijay Badrinarayanan, Alex Kendall and Roberto Cipolla "SegNet: A
Deep Convolutional Encoder-Decoder Architecture for Image
Segmentation." PAMI, (2017)
105
U-Net28
•
• Max pooling
Deconvolution
•
concat
• "U" U-
Net
28
“U-Net: Convolutional Networks for Biomedical Image Segmentation”,
Olaf Ronneberger, Philipp Fischer, Thomas Brox, 18 May 2015
106
PSPNet60
Pyramid Pooling Module
60
Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia, "Pyramid Scene Parsing Network", CVPR
(2017)
107
Pose Estimation
108
Pose Affinity Field33
•
CNN Convolutional Pose Machine
Part Affinity Field
CNN
• OpenPose
https://github.com/CMU-Perceptual-Computing-
Lab/openpose
• Geforce GTX 1080 9fps
33
Zhe Cao and Tomas Simon and Shih-En Wei and Yaser Sheikh,
"Realtime Multi-Person Pose Estimation using Part Affinity Fields", CVPR
(2017)
109
•
→ Faster
R-CNN
•
→
110
repeatability
reproducibility
repeatability reproducibility
repeatability
reproducibility
ACM Repeatability (same team, same experimental setup), Replicability
(different team, same experimental setup), Reproducibility (different
team, different experiental setup)
http://www.acm.org/publications/policies/artifact-review-badging
111
ChainerCV
https://github.com/chainer/chainercv
ChainerCV
•
•
•
• pre-trained
112
ChainerCV
113
- Faster R-CNN (VGG16-based, )
- SSD300, SSD512
:
- SegNet
- PSPNet (coming soon)
- PASCAL VOC (bounding box, segmentation)
- Stanford Online Products (classification)
- CamVid (segmentation)
- Caltech-UCSD Birds-200 (classification, key-points)
- Cityscapes (segmentation)
114
: pretrained-model
ChainerCV pretarined_model
model = FasterRCNNVGG16() #
# PASCAL VOC2007
model = FasterRCNNVGG16(pretrained_model='voc07')
model = SSD300(pretrained_model='voc0712')
model = SegNet(pretrained_model='camvid')
115
predict()
ChainerCV predict()
#
bboxes, labels, scores = model.predict(imgs)
#
labels = model.predict(imgs)
116
predict()
1.
2. forward
3. non-maximum
supression
117
[37] D. Xu, Y. Zhu, C. B. Choy, L. Fei-Fei, “Scene Graph
Generation by Iterative Message Passing”, CVPR (2017)
•
Faster R-CNN Region
Proposal network (RPN)
• RPN
…
•
118
ChainerCV
• Chainer
• public
•
from chainercv.datasets import VOCDetectionDataset
dataset = VOCDetectionDatset(split='trainval', year='2007')
# "trainval" 34
img, bbox, label = dataset[34]
119
ChainerCV transforms
•
data augmentation
• ChainerCV
data augmentation
•
• center_crop, pca_lighting, random_crop,
random_expand, random_flip, random_rotate,
ten_crop, etc...
120
ChainerCV transforms
TransformDataset Chainer
from chainercv import transforms
def transform(in_data):
img, bbox, label = in_data
img, param = transforms.random_flip(img, x_flip=True, return_param=True)
bbox = transforms.flip_bbox(bbox, x_flip=param['x_flip'])
return img, bbox, label
dataset = TransformDataset(dataset, transform)
bounding box
121
bounding box
ChainerCV
•
•
• bounding box
• matplotlib
122
ChainerCV
mean Intersection over Union (mIoU) mean
Average Precision (mAP)
Chainer Trainer Extension
# mAP Trainer Extension
evaluator = chainercv.extension.DetectionVOCEvaluator(iterator, model)
#
# e.g., result['main/map']
result = evaluator()
123
• https://github.com/chainer/chainercv
Faster R-CNN
SegNet
124
GAN
125
•
•
• RBM restricted boltzmann machine 34
Variational Auto-Encoder (VAE)35
Generative Adversarial Nets (GAN)
35
Diederik P Kingma and Max Welling, "Auto-Encoding Variational Bayes", ICLR (2014)
34
Smolensky, Paul, "Chapter 6: Information Processing in Dynamical Systems: Foundations of Harmony Theory",
Parallel Distributed Processing: Explorations in the Microstructure of Cognition (1986)
126
Generator
Discriminator
Dataset
OR from dataset?
Generative Adversarial Nets36
•
unsupervised learning
• G D
• D G
• G D
36
I. J. Goodfellowm, et. al., "Generative Adversarial Nets", NIPS (2014)
127
GAN
•
• Discriminator
• Generator Discriminator
128
GAN
•
Generator
• Generator
129
DCGAN37
• GAN
• Generator 1
Deconvolution
• Discriminator Generator
•
•
37
Alec Radford, Luke Metz, Soumith Chintala, "Unsupervised
Representation Learning with Deep Convolutional Generative Adversarial
Networks", ICLR (2016)
130
DCGAN37
• GAN DCGAN
• D
stride=2
• D Global Average Pooling
• D Leaky ReLU
• G D Batch Normalization G
D
37
Alec Radford, Luke Metz, Soumith Chintala, "Unsupervised
Representation Learning with Deep Convolutional Generative Adversarial
Networks", ICLR (2016)
131
Improved Techniques for Training GANs38
• GAN
• Feature matching: D fake real
• Minibatch discrimination: G D
1 mode cllapse
D
concat
•
38
T. Salimans, I. Goodfellow, et. al., "Improved Techniques for Training
GANs", NIPS (2016)
132
Improved Techniques for Training GANs38
• Generator
Semi-supervised
learning
• ImageNet DCGAN
• Inception score GAN
pre-trained model
38
T. Salimans, I. Goodfellow, et. al., "Improved Techniques for Training
GANs", NIPS (2016)
133
Wasserstein GAN (WGAN)39
(1)
• GAN Generator
Wasserstein Earth Mover's Distance
WGAN
• Generator 2
Wasserstein
39
Martin Arjovsky, Soumith Chintala, Léon Bottou, "Wasserstein GAN", arXiv:1701.07875 (2017)
134
Wasserstein GAN (WGAN)39
(2)
• WGAN Discriminator Wasserstein
• Discriminator(D)
D Wasserstein
•
39
Martin Arjovsky, Soumith Chintala, Léon Bottou, "Wasserstein GAN", arXiv:1701.07875 (2017)
135
Wasserstein GAN (WGAN)39
(3)
• WGAN Discriminator Wasserstein
Wasserstein
• Generator Wasserstein
• Generator Wasserstein
39
Martin Arjovsky, Soumith Chintala, Léon Bottou, "Wasserstein GAN", arXiv:1701.07875 (2017)
136
Wasserstein GAN (WGAN)39
(4)
1. Discriminator
2. 0.01
3. Generator
4.
39
Martin Arjovsky, Soumith Chintala, Léon Bottou, "Wasserstein GAN", arXiv:1701.07875 (2017)
137
WGAN with Gradient Penalty (WGAN-GP) 40
• WGAN Discriminator
Gradient Penalty
• Chainer v3
40
Gulrajani, Ishaan, et al. "Improved training of wasserstein gans." arXiv preprint arXiv:1704.00028 (2017).
138
Temporal Generative
Adversarial Nets (TGAN)41
• WGAN
•
Video Generator
Image Generator
41
Masaki Saito, Eiichi Matsumoto, Shunta Saito, "Temporal Generative
Adversarial Nets with Singular Value Clipping", ICCV (2017)
139
Temporal Generative
Adversarial Nets (TGAN)41
•
GAN WGAN
1
singular
value clipping
• Inception score
41
Masaki Saito, Eiichi Matsumoto, Shunta Saito, "Temporal Generative
Adversarial Nets with Singular Value Clipping", ICCV (2017)
140
SimGAN42
•
CG Refiner
• Refiner Discriminator
adversarial loss
self-regularization
• Apple, inc. CVPR 2017
"Improving the Realism of Synthetic Images"
42
A. Shrivastava, et. al. "Learning from Simulated and Unsupervised
Images through Adversarial Training", CVPR (2017)
141
Chainer-GAN-lib
GAN Chainer
Chainer Trainer GAN
https://github.com/pfnet-research/chainer-gan-lib
142
Adversarial examples70
• " "
•
NIPS 2017: Non-targeted Adversarial Attack
Google Brain "Non-
targeted"
70
Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy, "Explaining and
Harnessing Adversarial Examples." ICLR (2015)
143
144
NLP
•
• part-of-speech tagging
• word segmentation
• word sense
disambiguation
• named entity extraction
• syntactic parsing
• predicate-argument
recognition
145
NLP
•
•
•
146
147
RNN
• RNN (recurrent neural networks)
•
RNN
148
http://qiita.com/t_Signull/items/21b82be280b46f467d1b
LSTM
•
• 1 3
•
:
• 1
•
•
149
2.11
Gated recurrent unit
(GRU)
• LSTM
• reset 1
• update) 1
• GRU LSTM
150
RNN
one-hot
RNN
RNN
151
s.t.
perplexity; PPL 2
PPL PPL
152
1. Penn Treebank ptb
90 1
Chainer example ptb example
https://github.com/chainer/chainer/
tree/master/examples/ptb
2. One Biliion Word
8 80
3. Hutter
90MB/5MB/5MB
train/val/test
153
sequence-to-sequence
•
•
RNN
•
•
•
154
155
greedy algorithm
156
157
attention mechanism
LSTM
158
Attention is all you need65
RNN/CNN Attention Transformer
SOTA
Transformer: A Novel Neural Network
Architecture for Language Understanding
65
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion
Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, "Attention Is All
You Need", (2017)
159
160
policy
1.
2.
3.
4.
161
•
→ return
• discounted total reward
•
state value
162
state value function
optimal policy
163
action value function
164
greedy
ε-greedy
greedy
ε-greedy ε
greedy
165
Q Q-learning
Q
Q
166
Q (1)
Q Q
167
Q (2)
Q
Q
→MSE SGD
168
Deep Q-Network (DQN)43
• Q
• Q NN
DQN
• Experience replay
• Target Q-Network
• clipping
DQN SPACE INVADERS (uploaded by DeepMind)
43
Mnih, Volodymyr, et al. "Playing Atari with Deep Reinforcement
Learning", NIPS (2013)
169
DQN
Experience replay
- replay memory
- Q
Target Q-Network
-
Q
- Q $theta$ Q
clipping
- clip
170
• Q
•
•
171
•
172
• 45
•
45
Pierre Andry, et. al., "Learning invariant sensorimotor behaviors: A developmental approach to imitation
mechanisms." Adaptive behavior (2004)
173
Actor-Critic
• Actor
Critic
•
•
174
Asynchronous Advantage
Actor-Critic (A3C)44
•
•
Actor-Critic
• Experience replay
RNN
•
44
V. Mnih, et. al., "Asynchronous Methods for Deep Reinforcement
Learning", ICML (2016)
175
DDPG46
• Deep Deterministic Policy Gradient
(DDPG) Actor-Critic
• Deep Q-Network
End-to-End
•
Deep Reinforcement Learning
(DDPG) demonstration
46
Lillicrap, Timothy P., et al. "Continuous control with deep reinforcement
learning." arXiv preprint arXiv:1509.02971 (2015)
176
ChainerRL
•
Chainer
https://github.com/chainer/chainerrl
177
ChainerRL :
• ChainerRL OpenAI Gym Gym
• reset step
env = YourEnv()
# reset
obs = env.reset()
action = 0
# step
# 4
obs, r, done, info = env.step(action)
178
ChainerRL : (1)
•
• Chainer
Q
class CustomDiscreteQFunction(chainer.Chain):
def __init__(self):
super().__init__(l1=L.Linear(100, 50)
l2=L.Linear(50, 4))
def __call__(self, x, test=False):
h = F.relu(self.l1(x))
h = self.l2(h)
return chainerrl.action_value.DiscreteActionValue(h)
179
ChainerRL : (2)
class CustomGaussianPolicy(chainer.Chain):
def __init__(self):
super().__init__(l1=L.Linear(100, 50)
mean=L.Linear(50, 4),
var=L.Linear(50, 4))
def __call__(self, x, test=False):
h = F.relu(self.l1(x))
mean = self.mean(h)
var = self.var(h)
return chainerrl.distribution.GaussianDistribution(mean, var)
180
ChainerRL :
Q
Chainer Optimizer
q_func = CustomDiscreteQFunction()
optimizer = chainer.Adam()
optimizer.setup(q_func)
agent = chainerrl.agents.DQN(q_func, optimizer, ...) #
181
ChainerRL : (1)
ChainerRL
• ChainerRL
chainerrl.experiments.train_agent_with_evaluation(
agent, env, steps=100000, eval_frequency=10000, eval_n_runs=10, outdir='results')
182
ChainerRL : (1)
obs = env.reset()
r = 0
done = False
for _ in range(10000):
while not done:
action = agent.act_and_train(obs, r)
obs, r, done, info = env.step(action)
agent.stop_episode_and_train(obs, r, done)
obs = env.reset()
r, done = 0, False
agent.save('final_agent')
183
ChainerRL Quick Start
Guide
https://github.com/chainer/chainerrl/
blob/master/examples/quickstart/
quickstart.ipynb
OpenAI Gym DQN
184
Chainer
185

More Related Content

What's hot

PCAの最終形態GPLVMの解説
PCAの最終形態GPLVMの解説PCAの最終形態GPLVMの解説
PCAの最終形態GPLVMの解説弘毅 露崎
 
GAN(と強化学習との関係)
GAN(と強化学習との関係)GAN(と強化学習との関係)
GAN(と強化学習との関係)Masahiro Suzuki
 
帰納バイアスが成立する条件
帰納バイアスが成立する条件帰納バイアスが成立する条件
帰納バイアスが成立する条件Shinobu KINJO
 
ConvNetの歴史とResNet亜種、ベストプラクティス
ConvNetの歴史とResNet亜種、ベストプラクティスConvNetの歴史とResNet亜種、ベストプラクティス
ConvNetの歴史とResNet亜種、ベストプラクティスYusuke Uchida
 
【DL輪読会】DiffRF: Rendering-guided 3D Radiance Field Diffusion [N. Muller+ CVPR2...
【DL輪読会】DiffRF: Rendering-guided 3D Radiance Field Diffusion [N. Muller+ CVPR2...【DL輪読会】DiffRF: Rendering-guided 3D Radiance Field Diffusion [N. Muller+ CVPR2...
【DL輪読会】DiffRF: Rendering-guided 3D Radiance Field Diffusion [N. Muller+ CVPR2...Deep Learning JP
 
生成モデルの Deep Learning
生成モデルの Deep Learning生成モデルの Deep Learning
生成モデルの Deep LearningSeiya Tokui
 
[DL輪読会]“Highly accurate protein structure prediction with AlphaFold”
[DL輪読会]“Highly accurate protein structure prediction with AlphaFold”[DL輪読会]“Highly accurate protein structure prediction with AlphaFold”
[DL輪読会]“Highly accurate protein structure prediction with AlphaFold”Deep Learning JP
 
【論文調査】XAI技術の効能を ユーザ実験で評価する研究
【論文調査】XAI技術の効能を ユーザ実験で評価する研究【論文調査】XAI技術の効能を ユーザ実験で評価する研究
【論文調査】XAI技術の効能を ユーザ実験で評価する研究Satoshi Hara
 
Towards Total Recall in Industrial Anomaly Detection
Towards Total Recall in Industrial Anomaly DetectionTowards Total Recall in Industrial Anomaly Detection
Towards Total Recall in Industrial Anomaly Detectionharmonylab
 
時系列分析による異常検知入門
時系列分析による異常検知入門時系列分析による異常検知入門
時系列分析による異常検知入門Yohei Sato
 
匿名加工情報を使えないものか?(改訂版)
匿名加工情報を使えないものか?(改訂版)匿名加工情報を使えないものか?(改訂版)
匿名加工情報を使えないものか?(改訂版)Hiroshi Nakagawa
 
Prophet入門【Python編】Facebookの時系列予測ツール
Prophet入門【Python編】Facebookの時系列予測ツールProphet入門【Python編】Facebookの時系列予測ツール
Prophet入門【Python編】Facebookの時系列予測ツールhoxo_m
 
[DL輪読会]The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Se...
[DL輪読会]The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Se...[DL輪読会]The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Se...
[DL輪読会]The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Se...Deep Learning JP
 
合成経路探索 -論文まとめ- (PFN中郷孝祐)
合成経路探索 -論文まとめ-  (PFN中郷孝祐)合成経路探索 -論文まとめ-  (PFN中郷孝祐)
合成経路探索 -論文まとめ- (PFN中郷孝祐)Preferred Networks
 
アンサンブル木モデル解釈のためのモデル簡略化法
アンサンブル木モデル解釈のためのモデル簡略化法アンサンブル木モデル解釈のためのモデル簡略化法
アンサンブル木モデル解釈のためのモデル簡略化法Satoshi Hara
 
[DL輪読会]Transframer: Arbitrary Frame Prediction with Generative Models
[DL輪読会]Transframer: Arbitrary Frame Prediction with Generative Models[DL輪読会]Transframer: Arbitrary Frame Prediction with Generative Models
[DL輪読会]Transframer: Arbitrary Frame Prediction with Generative ModelsDeep Learning JP
 
Bayesian Neural Networks : Survey
Bayesian Neural Networks : SurveyBayesian Neural Networks : Survey
Bayesian Neural Networks : Surveytmtm otm
 
[DLHacks 実装] DeepPose: Human Pose Estimation via Deep Neural Networks
[DLHacks 実装] DeepPose: Human Pose Estimation via Deep Neural Networks[DLHacks 実装] DeepPose: Human Pose Estimation via Deep Neural Networks
[DLHacks 実装] DeepPose: Human Pose Estimation via Deep Neural NetworksDeep Learning JP
 
(2020.10) 分子のグラフ表現と機械学習: Graph Neural Networks (GNNs) とは?
(2020.10) 分子のグラフ表現と機械学習: Graph Neural Networks (GNNs) とは?(2020.10) 分子のグラフ表現と機械学習: Graph Neural Networks (GNNs) とは?
(2020.10) 分子のグラフ表現と機械学習: Graph Neural Networks (GNNs) とは?Ichigaku Takigawa
 

What's hot (20)

PCAの最終形態GPLVMの解説
PCAの最終形態GPLVMの解説PCAの最終形態GPLVMの解説
PCAの最終形態GPLVMの解説
 
GAN(と強化学習との関係)
GAN(と強化学習との関係)GAN(と強化学習との関係)
GAN(と強化学習との関係)
 
帰納バイアスが成立する条件
帰納バイアスが成立する条件帰納バイアスが成立する条件
帰納バイアスが成立する条件
 
外れ値
外れ値外れ値
外れ値
 
ConvNetの歴史とResNet亜種、ベストプラクティス
ConvNetの歴史とResNet亜種、ベストプラクティスConvNetの歴史とResNet亜種、ベストプラクティス
ConvNetの歴史とResNet亜種、ベストプラクティス
 
【DL輪読会】DiffRF: Rendering-guided 3D Radiance Field Diffusion [N. Muller+ CVPR2...
【DL輪読会】DiffRF: Rendering-guided 3D Radiance Field Diffusion [N. Muller+ CVPR2...【DL輪読会】DiffRF: Rendering-guided 3D Radiance Field Diffusion [N. Muller+ CVPR2...
【DL輪読会】DiffRF: Rendering-guided 3D Radiance Field Diffusion [N. Muller+ CVPR2...
 
生成モデルの Deep Learning
生成モデルの Deep Learning生成モデルの Deep Learning
生成モデルの Deep Learning
 
[DL輪読会]“Highly accurate protein structure prediction with AlphaFold”
[DL輪読会]“Highly accurate protein structure prediction with AlphaFold”[DL輪読会]“Highly accurate protein structure prediction with AlphaFold”
[DL輪読会]“Highly accurate protein structure prediction with AlphaFold”
 
【論文調査】XAI技術の効能を ユーザ実験で評価する研究
【論文調査】XAI技術の効能を ユーザ実験で評価する研究【論文調査】XAI技術の効能を ユーザ実験で評価する研究
【論文調査】XAI技術の効能を ユーザ実験で評価する研究
 
Towards Total Recall in Industrial Anomaly Detection
Towards Total Recall in Industrial Anomaly DetectionTowards Total Recall in Industrial Anomaly Detection
Towards Total Recall in Industrial Anomaly Detection
 
時系列分析による異常検知入門
時系列分析による異常検知入門時系列分析による異常検知入門
時系列分析による異常検知入門
 
匿名加工情報を使えないものか?(改訂版)
匿名加工情報を使えないものか?(改訂版)匿名加工情報を使えないものか?(改訂版)
匿名加工情報を使えないものか?(改訂版)
 
Prophet入門【Python編】Facebookの時系列予測ツール
Prophet入門【Python編】Facebookの時系列予測ツールProphet入門【Python編】Facebookの時系列予測ツール
Prophet入門【Python編】Facebookの時系列予測ツール
 
[DL輪読会]The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Se...
[DL輪読会]The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Se...[DL輪読会]The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Se...
[DL輪読会]The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Se...
 
合成経路探索 -論文まとめ- (PFN中郷孝祐)
合成経路探索 -論文まとめ-  (PFN中郷孝祐)合成経路探索 -論文まとめ-  (PFN中郷孝祐)
合成経路探索 -論文まとめ- (PFN中郷孝祐)
 
アンサンブル木モデル解釈のためのモデル簡略化法
アンサンブル木モデル解釈のためのモデル簡略化法アンサンブル木モデル解釈のためのモデル簡略化法
アンサンブル木モデル解釈のためのモデル簡略化法
 
[DL輪読会]Transframer: Arbitrary Frame Prediction with Generative Models
[DL輪読会]Transframer: Arbitrary Frame Prediction with Generative Models[DL輪読会]Transframer: Arbitrary Frame Prediction with Generative Models
[DL輪読会]Transframer: Arbitrary Frame Prediction with Generative Models
 
Bayesian Neural Networks : Survey
Bayesian Neural Networks : SurveyBayesian Neural Networks : Survey
Bayesian Neural Networks : Survey
 
[DLHacks 実装] DeepPose: Human Pose Estimation via Deep Neural Networks
[DLHacks 実装] DeepPose: Human Pose Estimation via Deep Neural Networks[DLHacks 実装] DeepPose: Human Pose Estimation via Deep Neural Networks
[DLHacks 実装] DeepPose: Human Pose Estimation via Deep Neural Networks
 
(2020.10) 分子のグラフ表現と機械学習: Graph Neural Networks (GNNs) とは?
(2020.10) 分子のグラフ表現と機械学習: Graph Neural Networks (GNNs) とは?(2020.10) 分子のグラフ表現と機械学習: Graph Neural Networks (GNNs) とは?
(2020.10) 分子のグラフ表現と機械学習: Graph Neural Networks (GNNs) とは?
 

Viewers also liked

[Dl輪読会]dl hacks輪読
[Dl輪読会]dl hacks輪読[Dl輪読会]dl hacks輪読
[Dl輪読会]dl hacks輪読Deep Learning JP
 
Chapter 8 ボルツマンマシン - 深層学習本読み会
Chapter 8 ボルツマンマシン - 深層学習本読み会Chapter 8 ボルツマンマシン - 深層学習本読み会
Chapter 8 ボルツマンマシン - 深層学習本読み会Taikai Takeda
 
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)Shunta Saito
 
How to go into production your machine learning models? #CWT2017
How to go into production your machine learning models? #CWT2017How to go into production your machine learning models? #CWT2017
How to go into production your machine learning models? #CWT2017Cloudera Japan
 
[DLHacks 実装]Network Dissection: Quantifying Interpretability of Deep Visual R...
[DLHacks 実装]Network Dissection: Quantifying Interpretability of Deep Visual R...[DLHacks 実装]Network Dissection: Quantifying Interpretability of Deep Visual R...
[DLHacks 実装]Network Dissection: Quantifying Interpretability of Deep Visual R...Deep Learning JP
 
ディープラーニングの産業応用とそれを支える技術
ディープラーニングの産業応用とそれを支える技術ディープラーニングの産業応用とそれを支える技術
ディープラーニングの産業応用とそれを支える技術Shohei Hido
 
オープンソースを利用した新時代を生き抜くためのデータ解析
オープンソースを利用した新時代を生き抜くためのデータ解析オープンソースを利用した新時代を生き抜くためのデータ解析
オープンソースを利用した新時代を生き抜くためのデータ解析nakapara
 
Twitter炎上分析事例 2014年
Twitter炎上分析事例 2014年Twitter炎上分析事例 2014年
Twitter炎上分析事例 2014年Takeshi Sakaki
 
最先端NLP勉強会 “Learning Language Games through Interaction” Sida I. Wang, Percy L...
最先端NLP勉強会“Learning Language Games through Interaction”Sida I. Wang, Percy L...最先端NLP勉強会“Learning Language Games through Interaction”Sida I. Wang, Percy L...
最先端NLP勉強会 “Learning Language Games through Interaction” Sida I. Wang, Percy L...Yuya Unno
 
[DL輪読会]Adversarial Feature Matching for Text Generation
[DL輪読会]Adversarial Feature Matching for Text Generation[DL輪読会]Adversarial Feature Matching for Text Generation
[DL輪読会]Adversarial Feature Matching for Text GenerationDeep Learning JP
 
「人工知能」の表紙に関するTweetの分析・続報
「人工知能」の表紙に関するTweetの分析・続報「人工知能」の表紙に関するTweetの分析・続報
「人工知能」の表紙に関するTweetの分析・続報Fujio Toriumi
 
第35回 強化学習勉強会・論文紹介 [Lantao Yu : 2016]
第35回 強化学習勉強会・論文紹介 [Lantao Yu : 2016]第35回 強化学習勉強会・論文紹介 [Lantao Yu : 2016]
第35回 強化学習勉強会・論文紹介 [Lantao Yu : 2016]Takayuki Sekine
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networksShuyo Nakatani
 
Approximate Scalable Bounded Space Sketch for Large Data NLP
Approximate Scalable Bounded Space Sketch for Large Data NLPApproximate Scalable Bounded Space Sketch for Large Data NLP
Approximate Scalable Bounded Space Sketch for Large Data NLPKoji Matsuda
 
RBM、Deep Learningと学習(全脳アーキテクチャ若手の会 第3回DL勉強会発表資料)
RBM、Deep Learningと学習(全脳アーキテクチャ若手の会 第3回DL勉強会発表資料)RBM、Deep Learningと学習(全脳アーキテクチャ若手の会 第3回DL勉強会発表資料)
RBM、Deep Learningと学習(全脳アーキテクチャ若手の会 第3回DL勉強会発表資料)Takuma Yagi
 
2016.03.11 「論文に書(け|か)ない自然言語処理」 ソーシャルメディア分析サービスにおけるNLPに関する諸問題について by ホットリンク 公開用
2016.03.11 「論文に書(け|か)ない自然言語処理」 ソーシャルメディア分析サービスにおけるNLPに関する諸問題について by  ホットリンク 公開用2016.03.11 「論文に書(け|か)ない自然言語処理」 ソーシャルメディア分析サービスにおけるNLPに関する諸問題について by  ホットリンク 公開用
2016.03.11 「論文に書(け|か)ない自然言語処理」 ソーシャルメディア分析サービスにおけるNLPに関する諸問題について by ホットリンク 公開用Takeshi Sakaki
 
あなたの業務に機械学習を活用する5つのポイント
あなたの業務に機械学習を活用する5つのポイントあなたの業務に機械学習を活用する5つのポイント
あなたの業務に機械学習を活用する5つのポイントShohei Hido
 

Viewers also liked (20)

k-means(k-平均法)
k-means(k-平均法)k-means(k-平均法)
k-means(k-平均法)
 
[Dl輪読会]dl hacks輪読
[Dl輪読会]dl hacks輪読[Dl輪読会]dl hacks輪読
[Dl輪読会]dl hacks輪読
 
Chapter 8 ボルツマンマシン - 深層学習本読み会
Chapter 8 ボルツマンマシン - 深層学習本読み会Chapter 8 ボルツマンマシン - 深層学習本読み会
Chapter 8 ボルツマンマシン - 深層学習本読み会
 
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
 
How to go into production your machine learning models? #CWT2017
How to go into production your machine learning models? #CWT2017How to go into production your machine learning models? #CWT2017
How to go into production your machine learning models? #CWT2017
 
Semantic segmentation2
Semantic segmentation2Semantic segmentation2
Semantic segmentation2
 
[DLHacks 実装]Network Dissection: Quantifying Interpretability of Deep Visual R...
[DLHacks 実装]Network Dissection: Quantifying Interpretability of Deep Visual R...[DLHacks 実装]Network Dissection: Quantifying Interpretability of Deep Visual R...
[DLHacks 実装]Network Dissection: Quantifying Interpretability of Deep Visual R...
 
ディープラーニングの産業応用とそれを支える技術
ディープラーニングの産業応用とそれを支える技術ディープラーニングの産業応用とそれを支える技術
ディープラーニングの産業応用とそれを支える技術
 
オープンソースを利用した新時代を生き抜くためのデータ解析
オープンソースを利用した新時代を生き抜くためのデータ解析オープンソースを利用した新時代を生き抜くためのデータ解析
オープンソースを利用した新時代を生き抜くためのデータ解析
 
Twitter炎上分析事例 2014年
Twitter炎上分析事例 2014年Twitter炎上分析事例 2014年
Twitter炎上分析事例 2014年
 
最先端NLP勉強会 “Learning Language Games through Interaction” Sida I. Wang, Percy L...
最先端NLP勉強会“Learning Language Games through Interaction”Sida I. Wang, Percy L...最先端NLP勉強会“Learning Language Games through Interaction”Sida I. Wang, Percy L...
最先端NLP勉強会 “Learning Language Games through Interaction” Sida I. Wang, Percy L...
 
[DL輪読会]Adversarial Feature Matching for Text Generation
[DL輪読会]Adversarial Feature Matching for Text Generation[DL輪読会]Adversarial Feature Matching for Text Generation
[DL輪読会]Adversarial Feature Matching for Text Generation
 
「人工知能」の表紙に関するTweetの分析・続報
「人工知能」の表紙に関するTweetの分析・続報「人工知能」の表紙に関するTweetの分析・続報
「人工知能」の表紙に関するTweetの分析・続報
 
第35回 強化学習勉強会・論文紹介 [Lantao Yu : 2016]
第35回 強化学習勉強会・論文紹介 [Lantao Yu : 2016]第35回 強化学習勉強会・論文紹介 [Lantao Yu : 2016]
第35回 強化学習勉強会・論文紹介 [Lantao Yu : 2016]
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
Argmax Operations in NLP
Argmax Operations in NLPArgmax Operations in NLP
Argmax Operations in NLP
 
Approximate Scalable Bounded Space Sketch for Large Data NLP
Approximate Scalable Bounded Space Sketch for Large Data NLPApproximate Scalable Bounded Space Sketch for Large Data NLP
Approximate Scalable Bounded Space Sketch for Large Data NLP
 
RBM、Deep Learningと学習(全脳アーキテクチャ若手の会 第3回DL勉強会発表資料)
RBM、Deep Learningと学習(全脳アーキテクチャ若手の会 第3回DL勉強会発表資料)RBM、Deep Learningと学習(全脳アーキテクチャ若手の会 第3回DL勉強会発表資料)
RBM、Deep Learningと学習(全脳アーキテクチャ若手の会 第3回DL勉強会発表資料)
 
2016.03.11 「論文に書(け|か)ない自然言語処理」 ソーシャルメディア分析サービスにおけるNLPに関する諸問題について by ホットリンク 公開用
2016.03.11 「論文に書(け|か)ない自然言語処理」 ソーシャルメディア分析サービスにおけるNLPに関する諸問題について by  ホットリンク 公開用2016.03.11 「論文に書(け|か)ない自然言語処理」 ソーシャルメディア分析サービスにおけるNLPに関する諸問題について by  ホットリンク 公開用
2016.03.11 「論文に書(け|か)ない自然言語処理」 ソーシャルメディア分析サービスにおけるNLPに関する諸問題について by ホットリンク 公開用
 
あなたの業務に機械学習を活用する5つのポイント
あなたの業務に機械学習を活用する5つのポイントあなたの業務に機械学習を活用する5つのポイント
あなたの業務に機械学習を活用する5つのポイント
 

Similar to Deep LearningフレームワークChainerと最近の技術動向

[論文読み]Interpretable Coun.ng for Visual Ques.on Answering
[論文読み]Interpretable Coun.ng for Visual Ques.on Answering[論文読み]Interpretable Coun.ng for Visual Ques.on Answering
[論文読み]Interpretable Coun.ng for Visual Ques.on Answeringhirono kawashima
 
Smart environment for industry 4.0
Smart environment for industry 4.0Smart environment for industry 4.0
Smart environment for industry 4.0JawadSajid2
 
Computer Graphics
Computer GraphicsComputer Graphics
Computer GraphicsAdri Jovin
 
Operationalizing Machine Learning Using GPU-accelerated, In-database Analytics
Operationalizing Machine Learning Using GPU-accelerated, In-database AnalyticsOperationalizing Machine Learning Using GPU-accelerated, In-database Analytics
Operationalizing Machine Learning Using GPU-accelerated, In-database AnalyticsKinetica
 
Python Raster Function - Esri Developer Conference - 2015
Python Raster Function - Esri Developer Conference - 2015Python Raster Function - Esri Developer Conference - 2015
Python Raster Function - Esri Developer Conference - 2015akferoz07
 
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...Balázs Hidasi
 
MAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsxMAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsxBharathiLakshmiAAssi
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)DonghyunKang12
 
Analysis of KinectFusion
Analysis of KinectFusionAnalysis of KinectFusion
Analysis of KinectFusionDong-Won Shin
 
Data quality evaluation & orbit identification from scatterometer
Data quality evaluation & orbit identification from scatterometerData quality evaluation & orbit identification from scatterometer
Data quality evaluation & orbit identification from scatterometerMudit Dholakia
 
Deep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr SanparitDeep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr SanparitBAINIDA
 
TechnicalBackgroundOverview
TechnicalBackgroundOverviewTechnicalBackgroundOverview
TechnicalBackgroundOverviewMotaz El-Saban
 
Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...
Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...
Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...TigerGraph
 
CONVOLUTIONAL NEURAL NETWORKS: The workhorse of image and video
CONVOLUTIONAL NEURAL NETWORKS: The workhorse of image and videoCONVOLUTIONAL NEURAL NETWORKS: The workhorse of image and video
CONVOLUTIONAL NEURAL NETWORKS: The workhorse of image and videoCristiano Rafael Steffens
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...MLconf
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakPyData
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA Taiwan
 
"A Fast Object Detector for ADAS using Deep Learning," a Presentation from Pa...
"A Fast Object Detector for ADAS using Deep Learning," a Presentation from Pa..."A Fast Object Detector for ADAS using Deep Learning," a Presentation from Pa...
"A Fast Object Detector for ADAS using Deep Learning," a Presentation from Pa...Edge AI and Vision Alliance
 

Similar to Deep LearningフレームワークChainerと最近の技術動向 (20)

[論文読み]Interpretable Coun.ng for Visual Ques.on Answering
[論文読み]Interpretable Coun.ng for Visual Ques.on Answering[論文読み]Interpretable Coun.ng for Visual Ques.on Answering
[論文読み]Interpretable Coun.ng for Visual Ques.on Answering
 
Smart environment for industry 4.0
Smart environment for industry 4.0Smart environment for industry 4.0
Smart environment for industry 4.0
 
Computer Graphics
Computer GraphicsComputer Graphics
Computer Graphics
 
Operationalizing Machine Learning Using GPU-accelerated, In-database Analytics
Operationalizing Machine Learning Using GPU-accelerated, In-database AnalyticsOperationalizing Machine Learning Using GPU-accelerated, In-database Analytics
Operationalizing Machine Learning Using GPU-accelerated, In-database Analytics
 
Python Raster Function - Esri Developer Conference - 2015
Python Raster Function - Esri Developer Conference - 2015Python Raster Function - Esri Developer Conference - 2015
Python Raster Function - Esri Developer Conference - 2015
 
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...
 
MAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsxMAtrix Multiplication Parallel.ppsx
MAtrix Multiplication Parallel.ppsx
 
matrixmultiplicationparallel.ppsx
matrixmultiplicationparallel.ppsxmatrixmultiplicationparallel.ppsx
matrixmultiplicationparallel.ppsx
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
Deep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLabDeep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLab
 
Analysis of KinectFusion
Analysis of KinectFusionAnalysis of KinectFusion
Analysis of KinectFusion
 
Data quality evaluation & orbit identification from scatterometer
Data quality evaluation & orbit identification from scatterometerData quality evaluation & orbit identification from scatterometer
Data quality evaluation & orbit identification from scatterometer
 
Deep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr SanparitDeep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr Sanparit
 
TechnicalBackgroundOverview
TechnicalBackgroundOverviewTechnicalBackgroundOverview
TechnicalBackgroundOverview
 
Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...
Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...
Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...
 
CONVOLUTIONAL NEURAL NETWORKS: The workhorse of image and video
CONVOLUTIONAL NEURAL NETWORKS: The workhorse of image and videoCONVOLUTIONAL NEURAL NETWORKS: The workhorse of image and video
CONVOLUTIONAL NEURAL NETWORKS: The workhorse of image and video
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
 
"A Fast Object Detector for ADAS using Deep Learning," a Presentation from Pa...
"A Fast Object Detector for ADAS using Deep Learning," a Presentation from Pa..."A Fast Object Detector for ADAS using Deep Learning," a Presentation from Pa...
"A Fast Object Detector for ADAS using Deep Learning," a Presentation from Pa...
 

More from Shunta Saito

Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to ChainerShunta Saito
 
[5 minutes LT] Brief Introduction to Recent Image Recognition Methods and Cha...
[5 minutes LT] Brief Introduction to Recent Image Recognition Methods and Cha...[5 minutes LT] Brief Introduction to Recent Image Recognition Methods and Cha...
[5 minutes LT] Brief Introduction to Recent Image Recognition Methods and Cha...Shunta Saito
 
A brief introduction to recent segmentation methods
A brief introduction to recent segmentation methodsA brief introduction to recent segmentation methods
A brief introduction to recent segmentation methodsShunta Saito
 
Building and road detection from large aerial imagery
Building and road detection from large aerial imageryBuilding and road detection from large aerial imagery
Building and road detection from large aerial imageryShunta Saito
 
DeepPose: Human Pose Estimation via Deep Neural Networks
DeepPose: Human Pose Estimation via Deep Neural NetworksDeepPose: Human Pose Estimation via Deep Neural Networks
DeepPose: Human Pose Estimation via Deep Neural NetworksShunta Saito
 
Building detection with decision fusion
Building detection with decision fusionBuilding detection with decision fusion
Building detection with decision fusionShunta Saito
 
Automatic selection of object recognition methods using reinforcement learning
Automatic selection of object recognition methods using reinforcement learningAutomatic selection of object recognition methods using reinforcement learning
Automatic selection of object recognition methods using reinforcement learningShunta Saito
 
強化学習入門
強化学習入門強化学習入門
強化学習入門Shunta Saito
 
視覚認知システムにおける知覚と推論
視覚認知システムにおける知覚と推論視覚認知システムにおける知覚と推論
視覚認知システムにおける知覚と推論Shunta Saito
 
集合知プログラミングゼミ第1回
集合知プログラミングゼミ第1回集合知プログラミングゼミ第1回
集合知プログラミングゼミ第1回Shunta Saito
 

More from Shunta Saito (11)

Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to Chainer
 
[5 minutes LT] Brief Introduction to Recent Image Recognition Methods and Cha...
[5 minutes LT] Brief Introduction to Recent Image Recognition Methods and Cha...[5 minutes LT] Brief Introduction to Recent Image Recognition Methods and Cha...
[5 minutes LT] Brief Introduction to Recent Image Recognition Methods and Cha...
 
A brief introduction to recent segmentation methods
A brief introduction to recent segmentation methodsA brief introduction to recent segmentation methods
A brief introduction to recent segmentation methods
 
LT@Chainer Meetup
LT@Chainer MeetupLT@Chainer Meetup
LT@Chainer Meetup
 
Building and road detection from large aerial imagery
Building and road detection from large aerial imageryBuilding and road detection from large aerial imagery
Building and road detection from large aerial imagery
 
DeepPose: Human Pose Estimation via Deep Neural Networks
DeepPose: Human Pose Estimation via Deep Neural NetworksDeepPose: Human Pose Estimation via Deep Neural Networks
DeepPose: Human Pose Estimation via Deep Neural Networks
 
Building detection with decision fusion
Building detection with decision fusionBuilding detection with decision fusion
Building detection with decision fusion
 
Automatic selection of object recognition methods using reinforcement learning
Automatic selection of object recognition methods using reinforcement learningAutomatic selection of object recognition methods using reinforcement learning
Automatic selection of object recognition methods using reinforcement learning
 
強化学習入門
強化学習入門強化学習入門
強化学習入門
 
視覚認知システムにおける知覚と推論
視覚認知システムにおける知覚と推論視覚認知システムにおける知覚と推論
視覚認知システムにおける知覚と推論
 
集合知プログラミングゼミ第1回
集合知プログラミングゼミ第1回集合知プログラミングゼミ第1回
集合知プログラミングゼミ第1回
 

Recently uploaded

What’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 UpdatesWhat’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 UpdatesVictoriaMetrics
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsSafe Software
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Cizo Technology Services
 
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptxReal-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptxRTS corp
 
Leveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + KobitonLeveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + KobitonApplitools
 
SAM Training Session - How to use EXCEL ?
SAM Training Session - How to use EXCEL ?SAM Training Session - How to use EXCEL ?
SAM Training Session - How to use EXCEL ?Alexandre Beguel
 
Best Angular 17 Classroom & Online training - Naresh IT
Best Angular 17 Classroom & Online training - Naresh ITBest Angular 17 Classroom & Online training - Naresh IT
Best Angular 17 Classroom & Online training - Naresh ITmanoharjgpsolutions
 
Introduction to Firebase Workshop Slides
Introduction to Firebase Workshop SlidesIntroduction to Firebase Workshop Slides
Introduction to Firebase Workshop Slidesvaideheekore1
 
Patterns for automating API delivery. API conference
Patterns for automating API delivery. API conferencePatterns for automating API delivery. API conference
Patterns for automating API delivery. API conferencessuser9e7c64
 
Comparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdfComparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdfDrew Moseley
 
VictoriaMetrics Q1 Meet Up '24 - Community & News Update
VictoriaMetrics Q1 Meet Up '24 - Community & News UpdateVictoriaMetrics Q1 Meet Up '24 - Community & News Update
VictoriaMetrics Q1 Meet Up '24 - Community & News UpdateVictoriaMetrics
 
Machine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their EngineeringMachine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their EngineeringHironori Washizaki
 
Effectively Troubleshoot 9 Types of OutOfMemoryError
Effectively Troubleshoot 9 Types of OutOfMemoryErrorEffectively Troubleshoot 9 Types of OutOfMemoryError
Effectively Troubleshoot 9 Types of OutOfMemoryErrorTier1 app
 
Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...Rob Geurden
 
How to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion ApplicationHow to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion ApplicationBradBedford3
 
Precise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalPrecise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalLionel Briand
 
Strategies for using alternative queries to mitigate zero results
Strategies for using alternative queries to mitigate zero resultsStrategies for using alternative queries to mitigate zero results
Strategies for using alternative queries to mitigate zero resultsJean Silva
 
VK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web DevelopmentVK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web Developmentvyaparkranti
 
Sending Calendar Invites on SES and Calendarsnack.pdf
Sending Calendar Invites on SES and Calendarsnack.pdfSending Calendar Invites on SES and Calendarsnack.pdf
Sending Calendar Invites on SES and Calendarsnack.pdf31events.com
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtimeandrehoraa
 

Recently uploaded (20)

What’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 UpdatesWhat’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 Updates
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data Streams
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
 
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptxReal-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
Real-time Tracking and Monitoring with Cargo Cloud Solutions.pptx
 
Leveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + KobitonLeveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
 
SAM Training Session - How to use EXCEL ?
SAM Training Session - How to use EXCEL ?SAM Training Session - How to use EXCEL ?
SAM Training Session - How to use EXCEL ?
 
Best Angular 17 Classroom & Online training - Naresh IT
Best Angular 17 Classroom & Online training - Naresh ITBest Angular 17 Classroom & Online training - Naresh IT
Best Angular 17 Classroom & Online training - Naresh IT
 
Introduction to Firebase Workshop Slides
Introduction to Firebase Workshop SlidesIntroduction to Firebase Workshop Slides
Introduction to Firebase Workshop Slides
 
Patterns for automating API delivery. API conference
Patterns for automating API delivery. API conferencePatterns for automating API delivery. API conference
Patterns for automating API delivery. API conference
 
Comparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdfComparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdf
 
VictoriaMetrics Q1 Meet Up '24 - Community & News Update
VictoriaMetrics Q1 Meet Up '24 - Community & News UpdateVictoriaMetrics Q1 Meet Up '24 - Community & News Update
VictoriaMetrics Q1 Meet Up '24 - Community & News Update
 
Machine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their EngineeringMachine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their Engineering
 
Effectively Troubleshoot 9 Types of OutOfMemoryError
Effectively Troubleshoot 9 Types of OutOfMemoryErrorEffectively Troubleshoot 9 Types of OutOfMemoryError
Effectively Troubleshoot 9 Types of OutOfMemoryError
 
Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...
 
How to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion ApplicationHow to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion Application
 
Precise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalPrecise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive Goal
 
Strategies for using alternative queries to mitigate zero results
Strategies for using alternative queries to mitigate zero resultsStrategies for using alternative queries to mitigate zero results
Strategies for using alternative queries to mitigate zero results
 
VK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web DevelopmentVK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web Development
 
Sending Calendar Invites on SES and Calendarsnack.pdf
Sending Calendar Invites on SES and Calendarsnack.pdfSending Calendar Invites on SES and Calendarsnack.pdf
Sending Calendar Invites on SES and Calendarsnack.pdf
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtime
 

Deep LearningフレームワークChainerと最近の技術動向