SlideShare a Scribd company logo
1 of 194
Download to read offline
Deep Learning
Yen-lung Tsai

Department of Mathematical Sciences
National Chengchi University
and
Seminar in Information Systems and Applications
Design Thinking
NTHU 2018
!2
Asking a good question
Learning Neural Networks
Applying Design Thinking
Outline
1
Asking a
Good Question
!3
!4
f
What we want to do is just transforming the real
world problem to a function. Then we use deep
learning techniques to find the function.
!5
Functions are solution
manuals
!6
I wan to know what
the animal in the
picture is.
!7
Question Answer
Formosan
black bear
Python
We have partial answers
!8
Quesiton Answer
Python
There might be infinitely many possible
cases that we haven’t seen beore
?
Formosan
black bear
!9
Finding our functions by Neural Networks!
!10
“Big 3” of Deep Learning
(Neural Works)
Standard NN CNN RNN
!11
Asking a Question
Seeing an animal in wild, we want to
know what is is?
1
!12
Transforming our
question into a function
f
Formosan
black bear
2
Preparing Data Sets for
Training
( , ) ( , “Python”), , ...
xk+1
, yk+1xk
, yk
x1
, y1 xn
, yn
Training Data Testing Data
3
“Formosan 

black bear”
!14
Reinforcement

Learning (RL)
Generative Adversarial 

Network (GAN)
VAE
Capsule
Standard NN CNN RNN
Constructing NN4
!15
Once we decide our structure of neural
network, we have a set of parameters need to
adjust.
θ = {wi, bj}
Once we determine the parameters, we have a
function:
!16
Learning
5
The learning is sent to our neural network using
our training data, adjusting our parameters,
and then using a loss function to see how much
difference we have and the observed value.
!17
Basically, we use the method called:
gradient descent
For Neural Networks, the method is also called:
backpropagation
!18
I want to know the
closing price of a
stock tomorrow.
!19
fDate x
the closing price of
a stock x
!20
f
Use the prices of the
previous week to predict
the price for the next day.
NN, CNN, RNN
!21
I want to know how
may homers a
particular MLB
player can hit in 2018
season.
!22
Player
preformance
in the year of
t-1
[Age, G, PA, AB, R, H, 2B, 3B, HR,
RBI, SB, BB, SO, OPS+, TB]
15 features!
f
Number of
homers in the
year of t
RNN
!23
Chatbot
!24
fCurrent word Next word
!25
W1 W2
R1
EOS R1
R2
Rk
EOS
Note that in this mode, each input and output
is not of fixed length!
!26
I want to use AI to
play games (drive a
car, brew coffee...)
!27
π
The best
action
CNN + NN
!28
Q Score
Reinforcement Learning
+
Left
!29
some characters
are missing in a
font I like
!30
f
Font A Font B
CNN, VAE, GAN
2
AI Core Technology -
Principles of 

Neural Networks
!31
Remember we just have to
learn a function
!32
f
x1
x2
xn
y1
y2
ym
!33
Three Steps of Learning
Functions
Transfer a real world problem into a function.
Collect training materials that we know "correct
answers."
Find the function!
Black Box Learning
There are really techniques for learning
arbitrary functions
!34
neural networks
!35
In the 1980-1990 or so, it
is a pretty fancy stuff.
!36
!37
Hidden
Layer
Output
Layer
Input
Layer
Black Box
What is powerful is that neural
networks will learn everything!
And you don't have to tell it what the
function should look like: linear, quadratic
polynomial, and so on.
!38
Open the
Black Box!
!39
!40
Fully Connected Neural
Networks
Very popular since 1980s
Standard NN
!41
The action of every neuron
is basically the same!
!42
!43
Each neuron accepts
several inputs and then
sends one output.
!44
Find the weighted
sum of inputs.
!45
Plus bias.
!46
Apply the activation
function to the weighted
sum.
!47
Popular activation functions
ReLU Sigmoid Gaussian
!48
Parameters are weights, biases
!49
“Learned” neural network
1
2
1
21 1
!50
Suppose we have the input
21 1
(x1
,x2
) = (1,3)
1
3
1 3
8
1
2
1
!51
Using ReLU as activation functions
1
3
1
2
1
!52
NN needs to be trained
Using “previous exam
questions” to train our
neural network
Learning method is called
backpropagation
Training Methods
When a neural network structure is determined
and activation functions are also determined,
it can be adjusted by weights, biases. We call
the set of these parameters θ, each of which
defines a function, and we treat it as a set.
The Function Space of our NN
!53
We are looking for
Makes the closest to the objective
function
!54
What does “the closest” mean
That means the value of “loss function” is
minimum
!55
Suppose we have the
training data
!56
!57
We the value is as small as possible
The most popular loss
function
What’s
this!?
!58
x 網路路輸出 真正的 誤差
1 2 3 1
2 5 2 -3
3 6 8 2
4 7 2 -5
5 6 6 0
6 4 8 4
7 8 9 1
How to
calculate total
error?
!59
x 網路路輸出 真正的 誤差
1 2 3 1
2 5 2 -3
3 6 8 2
4 7 2 -5
5 6 6 0
6 4 8 4
7 8 9 1
Total = 0!!
Can we just
add them up?
!60
x 網路路輸出 真正的 誤差
1 2 3 1
2 5 2 -3
3 6 8 2
4 7 2 -5
5 6 6 0
6 4 8 4
7 8 9 1
Squared
Sum
1
9
4
25
0
16
1
56 in total
!61
Basically, do such
adjustment
learning rate
What does this
terrible thing mean?
!62
Remember that L is a
function of w1, w2, b1,
!63
The smaller the better
For simplification, we first
think of L has only one
variable w
!64
!65
Current value of w
How to get to
the minimum?
!66
Current value of w
I know, a point to
move to the right!
!67
How does the
computer “see” it?
!68
Tangent is the key!
!69
Tangent slope < 0
!70
Tangent slope > 0
The slope of the tangent
points to the (local)
maximum direction!
!71
!72
Tangent slope is the
rate of change
Tangent slope
Tangent slope
!73
Pointing (local) maximum
Tangent slope
Tangent slope
!74
Moving toward (local) minimaKey
In order to make the value of the loss
function L smaller, we should adjust the
weight w:
!75
Suppose current w=a, we should update our
w as:
Moving toward (local) minimaKey
!76
Adjusting the Weight
Tangent slope
!77
Sometimes it
will run over!
Tangent slope
!78
In order not to make too much adjustment
at one time, we will multiply a small
number called Leraning Rate:
Moving toward (local) minimaKey
!79
However, there are
more than one
parameter
!80
Example
Suppose that
And we are moving toward to local minimum.
!81
Pretend to have only
one parameter!
say, it is w1
!82
All parameters are fixed, except w1
One-variable function!
例⼦
!83
Similarly, we can also define
Example
!84
So we can adjust w1, w2, b1, and make L
smaller and smaller
w1
w2
b1
Example
!85
Writing together seems more learned!
Updated
We call this the
gradient of L
Example
!86
Partial DerivativeDefinition
What we have done is just so called partial
derivatives.
!87
Similarly,
Partial DerivativeDefinition
!88
gradientNotation
Recall the gradient of L is:
!89
We should have cool notation for the
gradient:
gradientNotation
!90
So we can update all parameters by the
formula:
gradientNotation
This “learning method” has a
fancy name
Gradient Descent
!91
!92
Deep Learning 

Big 3
Standard NN CNN RNN
!93
No Kidding!
!94
Convolutional Neural Network
Super star for image
recognition
CNN
!95
Formosan black bear
image recognition
f ( ) =
!96
Playing Video Games
Current states “the best” actionπ ( ) =
reinforcement learning
!97
filter 1
filter 2
input
每個 filter 看⼀一個特徵, 掃過每
⼀一個點, 紀錄該點附近的「特
徵強度」。
Convolutional Neural Network (CNN)
!98
Convolutional Layer
1
!99
Say, 3x3 filters
We need some “filters”
!100
2 5 5 2 5 2 0 1
2 3 4 0 4 2 1 5
4 3 1 3 5 5 4 3
5 3 4 5 0 2 1 5
2 3 1 1 1 0 1 3
4 4 1 1 5 1 1 4
2 3 2 2 0 4 2 4
0 5 4 5 3 4 1 4
35
Think this is an image.
filter
Dot product
This is learned.
W=
!101
2 5 5 2 5 2 0 1
2 3 4 0 4 2 1 5
4 3 1 3 5 5 4 3
5 3 4 5 0 2 1 5
2 3 1 1 1 0 1 3
4 4 1 1 5 1 1 4
2 3 2 2 0 4 2 4
0 5 4 5 3 4 1 4
35 27
filter
Move to the right
Same matrix
as before!
W=
!102
2 5 5 2 5 2 0 1
2 3 4 0 4 2 1 5
4 3 1 3 5 5 4 3
5 3 4 5 0 2 1 5
2 3 1 1 1 0 1 3
4 4 1 1 5 1 1 4
2 3 2 2 0 4 2 4
0 5 4 5 3 4 1 4
35 27 44 32 36 38
36 36 37 36 36 43
37 37 23 26 17 35
29 25 22 18 14 27
27 25 24 21 24 32
31 38 27 34 25 40
filter
All the way to the end
W=
!103
Neurons look like this
!104
2 5 5 2 5 2 0 1
2 3 4 0 4 2 1 5
4 3 1 3 5 5 4 3
5 3 4 5 0 2 1 5
2 3 1 1 1 0 1 3
4 4 1 1 5 1 1 4
2 3 2 2 0 4 2 4
0 5 4 5 3 4 1 4
35 27 44 32 36 38
36 36 37 36 36 43
37 37 23 26 17 35
29 25 22 18 14 27
27 25 24 21 24 32
31 38 27 34 25 40
filter
The points on the
picture are one input
layer neuron
W=
!105
2 5 5 2 5 2 0 1
2 3 4 0 4 2 1 5
4 3 1 3 5 5 4 3
5 3 4 5 0 2 1 5
2 3 1 1 1 0 1 3
4 4 1 1 5 1 1 4
2 3 2 2 0 4 2 4
0 5 4 5 3 4 1 4
35 27 44 32 36 38
36 36 37 36 36 43
37 37 23 26 17 35
29 25 22 18 14 27
27 25 24 21 24 32
31 38 27 34 25 40
filter
Conv layers also consist
lots of neural
W=
!106
2 5 5 2 5 2 0 1
2 3 4 0 4 2 1 5
4 3 1 3 5 5 4 3
5 3 4 5 0 2 1 5
2 3 1 1 1 0 1 3
4 4 1 1 5 1 1 4
2 3 2 2 0 4 2 4
0 5 4 5 3 4 1 4
35 27 44 32 36 38
36 36 37 36 36 43
37 37 23 26 17 35
29 25 22 18 14 27
27 25 24 21 24 32
31 38 27 34 25 40
filter
The two layers are not completely connected
W=
!107
2 5 5 2 5 2 0 1
2 3 4 0 4 2 1 5
4 3 1 3 5 5 4 3
5 3 4 5 0 2 1 5
2 3 1 1 1 0 1 3
4 4 1 1 5 1 1 4
2 3 2 2 0 4 2 4
0 5 4 5 3 4 1 4
35 27 44 32 36 38
36 36 37 36 36 43
37 37 23 26 17 35
29 25 22 18 14 27
27 25 24 21 24 32
31 38 27 34 25 40
filter
the weights are shared

(same as previous ones)
W=
!108
35 27 44 32 36 38
36 36 37 36 36 43
37 37 23 26 17 35
29 25 22 18 14 27
27 25 24 21 24 32
31 38 27 34 25 40
Finally, we get a 6x6 matrix,
and actually we usually
make it a 8x8 matrix.
And we have a lot of filters!
!109
Max-Pooling Layer
2
!110
We have to decide the size of area to have one
representative. Say, 2x2.
Basically it is “voting”
!111
35 27 44 32 36 38
36 36 37 36 36 43
37 37 23 26 17 35
29 25 22 18 14 27
27 25 24 21 24 32
31 38 27 34 25 40
36 44 43
37 26 35
38 34 40
“Vote” for the largest number!!
!112
convolution, max-pooling, convolution, 

max-pooling…
We can repeat and repeat
!113
After we finished, we sent
outputs to “normal”
neural networks.
!114
Recurrent Neural Network
Neural Netowork with
memory
RNN
!115
Chatbot
Current word Next wordf ( ) =
!116
fCurrent word Next word
!117
W1 W2
R1
EOS R1
R2
Rk
EOS
ChatbotApplication
!118
In fact, the input does not
have to be text, but it is also
possible that the video (one
by one) is output! The
output can still be text, and
the most common is
probably to let the
computer say what
happened in the video.
!119
Translater
Video Captioning Generator
Context Generator
Drawing
Applications
!120
Andrej Karpathy use RNN to generate a book in
“Stacks” (a deep topic in Algebraic Geometry)
http://karpathy.github.io/2015/05/21/rnn-
effectiveness/
!121
PANDARUS:
Alas, I think he shall be come
approached and the day
When little srain would be attain'd into
being never fed,
And who is but a chain and subjects of
his death,
I should not sleep.
Second Senator:
They are away this miseries, produced
upon my soul,
Breaking and strongly should be
buried, when I perish
The earth and thoughts of many states.
“Shakespeare”
!122
Usually, outputs of a Neural
Network are not affected by the
input orders..
!123
However, RNN cells will use previous
outputs as part of inputs
!124
The “unfold” presentation.
!125
Recurrent Neural Network (RNN)
ht
1
= σ (w1
xt
1
+ w2
xt
2
+ w3
h3
t−1
+ w4
h4
t−1
+ b1
)
會加入上⼀一次的
outputs 當這次的
inputs。
!126
Remark
To make it easier for everyone to understand, we
will use simpler representations. Please note
that the inputs are vectors and will have
respected weight; while the outputs are scalars.
xt =
⎡
⎢
⎢
⎢
⎣
xt,1
xt,2
...
xt,n
⎤
⎥
⎥
⎥
⎦
Looks like this
!127
Actually look like this
Remark
!128
h’s work similarly
Remark
!129
Each cell of some
layer, there is one
output.
Inputs could
be vectors
The k-th RNN Cell
!130
The connections of a RNN
layer. Note that RNN cells
will pass their outputs to
other RNN Cells of same
layer.
!131
Formula for the
output of a
standard RNN cell.
!132
LSTM
GRU
Long Short Term Memory
Gated Recurrent Unit
When we say “RNN,” most people
actually think of
!133
LSTM
Long Short Term Memory
The Ace of RNNs
!134
k-th

LSTM
Cell
Cell status
!135
Gate
Important
!136
The output is a number
between 0 and 1
sigmoid
Just decide how big the
“gate” will open
!137
LSTMs has three
types of Gates
!138
forget gate input gate output gate
!139
Recall
tanh
sigmoid
!140
-1
1
!141
0
1
σ(x) =
1
1 + e−x
!142
k-th

LSTM cell
LSTM Again The cell state is for
the cell only
The output of a cell
will “share” with
other cells
!143
“New” cell status
!144
!145
Do we really need to make
things so complicated?
!146
GRU
Gated Recurrent Unit
Simplified version of LSTM
!147
Although it has “gated” in the name
Only 2 Gates
!148
reset gateupdate gate
!149
We could ignore
previous inputs
!150
!151
Key Names of RNNs
Now talking about RNN, in fact,
including the original RNN, LSTM,
GRU and other variants.
In particular, the original RNN is
called Vanilla RNN, and is
SimpleRNN in Keras.
3
Design thinking,
creative problem
solving
!152
!153
Empathize Define Ideate Prototype Test
Design Thinking Process
(Standford d.school)
Very close to the engineer’s approach
!154
Our model is rarely successful
for the first time.
—Yi-Shin Chen, National Tsing Hua University
“ ”
!155
MLB Player Home Runs Prediction
!156
Year t-1

[Age, G, PA, AB, R, H, 2B, 3B, HR,
RBI, SB, BB, SO, OPS+, TB]
15 features
Number of
homers in the
year of t
f
!157
Use LSTM. Input the data in a period of 10 years and
predict the home runs in the next year.
Only one LSTM layer!
!158
Don't guess the
exact number, guess
which interval!
divided into 5 subintervals: 

0-9, 10-19, 20-29, 30-39, 40+
!159
1
3
2
4
5
10-19
One-Hot encoding
0
1
0
0
0
⎡
⎣
⎢
⎢
⎢
⎢
⎢
⎢
⎤
⎦
⎥
⎥
⎥
⎥
⎥
⎥
0-9
10-19
20-29
30-39
40+
!160
Mike Trout (LAA)
Predicted 30-39
Actual 33
Mookie Betts (BOS)
Predicted 20-29
Actual 24
Jose Altuve (HOU)
Predicted 20-29
Actual 24
Kris Bryant (CHC)
Predicted 30-39
Actual 29
Daniel Murphy (WSH)
Predicted 20-29
Actual 23
Corey Seager (LAD)
Predicted 20-29
Actual 22
2017 forecast result
!161
Fancy ways to ask
questions!
!162
VAE
Standard NN CNN RNN
Reinforcement

Learning (RL)
Generative Adversarial 

Network (GAN)
Capsule
!163
Generative Adversarial
Network
Yann LeCun said GNN is the
most promising model
GAN
!164
There are many interesting recent
development in deep learning…
The most important one, in my opinion, is
adversarial training (also called GAN for
Generative Adversarial Networks). 
”
“
—Yan LeCun (楊⽴昆), 2016
!165
The GAN Zoo
https://github.com/hindupuravinash/
the-gan-zoo
!166
generatorNoise
discriminator
Real or Fake
A GAN consists two neural networks,
a Generator and a Discirminator.
z
x
G
D
G(z)
!167
Want
Close to 1
Want
Close to 0
Close to 1
D, G PK!
Discriminator
D
Generator
G
!168
Jun-Yan Zhu et al. (ECCV 2016)
“Generative Visual Manipulation on the Natural Image Manifold”
iGAN
https://arxiv.org/abs/1609.03552
!169
Every one can draw!
https://youtu.be/9c4z6YsBGQ0
!170
Karras et al. NVIDIA team, (ICLR 2018)
“Progressive Growing of GANs for Improved Quality, Stability, and Variation”
Progressive GAN
https://arxiv.org/abs/1710.10196
!171
Karras-Aila-Laine-Lehtinen
By a NVIDIA team
Theano, Python 2, single GPU (Hey, it’s NVIDIA)
Progressive Growing of GANs for Improved
Quality, Stability, and Variation
!172
These are fake (1024x1024)
!173
Isola, Zhu, et al., (CVPR 2017)
“Image-to-Image Translation with Conditional Adversarial Networks”
Pix2Pix
https://arxiv.org/abs/1611.07004
!174
* From the original paper of Isola, Zhu et al. (2017)
Pix2pix transfers satellite images to maps
!175
Pix2pix generates street views
* From the original paper of Isola, Zhu et al. (2017)
!176
* by Christopher Hesse
Pix2pix On-line Version
https://affinelayer.com/pixsrv/
!177
Jun-Yan Zhu et al. (ICCV 2017)
“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”
CycleGAN
https://arxiv.org/abs/1703.10593
!178
G

Generator
F

Generator
Domain
A
Domain
B
Discriminator
B
Discriminator
A
CycleGAN
!179
Don’t need to pair
our data sets!!
And open infinitely many possibilities...
!180
Horses to Zebras!!
https://youtu.be/9reHvktowLY
!181
One example from authors of CycleGAN
!182
Face-off (Tzer-Jen Wei)
https://youtu.be/Fea4kZq0oFQ
!183
Reinforcement Learning
AlphaGo key technique
Reinforcement Learning
!184
Agent

(computer)
Environment state
action
reward
rt
!185
Let’s play!
!186
π
Left
1 Policy Based
Right
or
State Action
policy function
!187
Usually it is not easy to
learn directly...
!188
Q Grade
+
Action
2 Value Based
(Usually
estimate
reward)
Value function
!189
Netflix AlphaGo Film (Highly Recommended)
!190
Self-driving cars
!191
Automated trading
system
!192
Fixed one ETF each time
Start with $20,000
Work for one year (Sell all ETF at the end)
Using reinforcement learning
* ETF data provided by the Global
Intelligence
!193
Data from past month
(20 days, in a 20x6
matrix)
f
1
2
3
4
5
Buy 20 units
Buy 10 units
No trading
Sell 10 units
Sell 20 units
5 possible actions
!194
CDQN Hold & buy CDQN Hold & buy
ETF1 17.71% 10.89% ETF11 10.76% 5.26%
ETF2 16.53% 12.6% ETF12 10.19% 13.17%
ETF3 16.3% 0.35% ETF13 7.8% 1.42%
ETF4 14.4% 13.25% ETF14 6.23% 3.56%
ETF5 14.3% 12.7% ETF15 5.73% 4.61%
ETF6 13.91% 13.37% ETF16 3.78% -12.76%
ETF7 13.17% 10.52% ETF17 2.85% 5.83%
ETF8 12.35% 17.07% ETF18 1.59% -4.45%
ETF9 11.68% 10.81% ETF19 1.07% -18.09%
ETF10 11.09% 8.14% ETF20 -0.59% -0.75%
Trading Results

More Related Content

What's hot

Back propagation
Back propagationBack propagation
Back propagationSan Kim
 
AlphaZero and beyond: Polygames
AlphaZero and beyond: PolygamesAlphaZero and beyond: Polygames
AlphaZero and beyond: PolygamesOlivier Teytaud
 
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법NAVER Engineering
 
Using Topological Data Analysis on your BigData
Using Topological Data Analysis on your BigDataUsing Topological Data Analysis on your BigData
Using Topological Data Analysis on your BigDataAnalyticsWeek
 
Variational Autoencoded Regression of Visual Data with Generative Adversarial...
Variational Autoencoded Regression of Visual Data with Generative Adversarial...Variational Autoencoded Regression of Visual Data with Generative Adversarial...
Variational Autoencoded Regression of Visual Data with Generative Adversarial...NAVER Engineering
 
Evolutionary deep learning: computer vision.
Evolutionary deep learning: computer vision.Evolutionary deep learning: computer vision.
Evolutionary deep learning: computer vision.Olivier Teytaud
 
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...宏毅 李
 
How DeepMind Mastered The Game Of Go
How DeepMind Mastered The Game Of GoHow DeepMind Mastered The Game Of Go
How DeepMind Mastered The Game Of GoTim Riser
 
Gan 발표자료
Gan 발표자료Gan 발표자료
Gan 발표자료종현 최
 
Multimodal Residual Learning for Visual Question-Answering
Multimodal Residual Learning for Visual Question-AnsweringMultimodal Residual Learning for Visual Question-Answering
Multimodal Residual Learning for Visual Question-AnsweringNAVER D2
 
Deep Learning & Tensor flow: An Intro
Deep Learning & Tensor flow: An IntroDeep Learning & Tensor flow: An Intro
Deep Learning & Tensor flow: An IntroSiby Jose Plathottam
 
30 分鐘學會實作 Python Feature Selection
30 分鐘學會實作 Python Feature Selection30 分鐘學會實作 Python Feature Selection
30 分鐘學會實作 Python Feature SelectionJames Huang
 
Graph convolutional networks in apache spark
Graph convolutional networks in apache sparkGraph convolutional networks in apache spark
Graph convolutional networks in apache sparkEmiliano Martinez Sanchez
 
Baisc Deep Learning HandsOn
Baisc Deep Learning HandsOnBaisc Deep Learning HandsOn
Baisc Deep Learning HandsOnSean Yu
 
KDD Cup 2021 時系列異常検知コンペ 参加報告
KDD Cup 2021 時系列異常検知コンペ 参加報告KDD Cup 2021 時系列異常検知コンペ 参加報告
KDD Cup 2021 時系列異常検知コンペ 参加報告GentaYoshimura
 
TensorFlow 深度學習快速上手班--機器學習
TensorFlow 深度學習快速上手班--機器學習TensorFlow 深度學習快速上手班--機器學習
TensorFlow 深度學習快速上手班--機器學習Mark Chang
 
Deep Learning: Recurrent Neural Network (Chapter 10)
Deep Learning: Recurrent Neural Network (Chapter 10) Deep Learning: Recurrent Neural Network (Chapter 10)
Deep Learning: Recurrent Neural Network (Chapter 10) Larry Guo
 
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기NAVER Engineering
 
[한국어] Safe Multi-Agent Reinforcement Learning for Autonomous Driving
[한국어] Safe Multi-Agent Reinforcement Learning for Autonomous Driving[한국어] Safe Multi-Agent Reinforcement Learning for Autonomous Driving
[한국어] Safe Multi-Agent Reinforcement Learning for Autonomous DrivingKiho Suh
 
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...Altoros
 

What's hot (20)

Back propagation
Back propagationBack propagation
Back propagation
 
AlphaZero and beyond: Polygames
AlphaZero and beyond: PolygamesAlphaZero and beyond: Polygames
AlphaZero and beyond: Polygames
 
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
 
Using Topological Data Analysis on your BigData
Using Topological Data Analysis on your BigDataUsing Topological Data Analysis on your BigData
Using Topological Data Analysis on your BigData
 
Variational Autoencoded Regression of Visual Data with Generative Adversarial...
Variational Autoencoded Regression of Visual Data with Generative Adversarial...Variational Autoencoded Regression of Visual Data with Generative Adversarial...
Variational Autoencoded Regression of Visual Data with Generative Adversarial...
 
Evolutionary deep learning: computer vision.
Evolutionary deep learning: computer vision.Evolutionary deep learning: computer vision.
Evolutionary deep learning: computer vision.
 
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
 
How DeepMind Mastered The Game Of Go
How DeepMind Mastered The Game Of GoHow DeepMind Mastered The Game Of Go
How DeepMind Mastered The Game Of Go
 
Gan 발표자료
Gan 발표자료Gan 발표자료
Gan 발표자료
 
Multimodal Residual Learning for Visual Question-Answering
Multimodal Residual Learning for Visual Question-AnsweringMultimodal Residual Learning for Visual Question-Answering
Multimodal Residual Learning for Visual Question-Answering
 
Deep Learning & Tensor flow: An Intro
Deep Learning & Tensor flow: An IntroDeep Learning & Tensor flow: An Intro
Deep Learning & Tensor flow: An Intro
 
30 分鐘學會實作 Python Feature Selection
30 分鐘學會實作 Python Feature Selection30 分鐘學會實作 Python Feature Selection
30 分鐘學會實作 Python Feature Selection
 
Graph convolutional networks in apache spark
Graph convolutional networks in apache sparkGraph convolutional networks in apache spark
Graph convolutional networks in apache spark
 
Baisc Deep Learning HandsOn
Baisc Deep Learning HandsOnBaisc Deep Learning HandsOn
Baisc Deep Learning HandsOn
 
KDD Cup 2021 時系列異常検知コンペ 参加報告
KDD Cup 2021 時系列異常検知コンペ 参加報告KDD Cup 2021 時系列異常検知コンペ 参加報告
KDD Cup 2021 時系列異常検知コンペ 参加報告
 
TensorFlow 深度學習快速上手班--機器學習
TensorFlow 深度學習快速上手班--機器學習TensorFlow 深度學習快速上手班--機器學習
TensorFlow 深度學習快速上手班--機器學習
 
Deep Learning: Recurrent Neural Network (Chapter 10)
Deep Learning: Recurrent Neural Network (Chapter 10) Deep Learning: Recurrent Neural Network (Chapter 10)
Deep Learning: Recurrent Neural Network (Chapter 10)
 
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
 
[한국어] Safe Multi-Agent Reinforcement Learning for Autonomous Driving
[한국어] Safe Multi-Agent Reinforcement Learning for Autonomous Driving[한국어] Safe Multi-Agent Reinforcement Learning for Autonomous Driving
[한국어] Safe Multi-Agent Reinforcement Learning for Autonomous Driving
 
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
 

Similar to Deep Learning and Design Thinking

Exact Real Arithmetic for Tcl
Exact Real Arithmetic for TclExact Real Arithmetic for Tcl
Exact Real Arithmetic for Tclke9tv
 
Machine Learning on Azure - AzureConf
Machine Learning on Azure - AzureConfMachine Learning on Azure - AzureConf
Machine Learning on Azure - AzureConfSeth Juarez
 
Understanding Basics of Machine Learning
Understanding Basics of Machine LearningUnderstanding Basics of Machine Learning
Understanding Basics of Machine LearningPranav Ainavolu
 
Cynthia Lee ITEM 2018
Cynthia Lee ITEM 2018Cynthia Lee ITEM 2018
Cynthia Lee ITEM 2018ITEM
 
How to Explain Post-Quantum Cryptography to a Middle School Student - Klaus S...
How to Explain Post-Quantum Cryptography to a Middle School Student - Klaus S...How to Explain Post-Quantum Cryptography to a Middle School Student - Klaus S...
How to Explain Post-Quantum Cryptography to a Middle School Student - Klaus S...44CON
 
20190417 畳み込みニューラル ネットワークの基礎と応用
20190417 畳み込みニューラル ネットワークの基礎と応用20190417 畳み込みニューラル ネットワークの基礎と応用
20190417 畳み込みニューラル ネットワークの基礎と応用Kazuki Motohashi
 
Neural networks - BigSkyDevCon
Neural networks - BigSkyDevConNeural networks - BigSkyDevCon
Neural networks - BigSkyDevConryanstout
 
Beating Floating Point at its Own Game: Posit Arithmetic
Beating Floating Point at its Own Game: Posit ArithmeticBeating Floating Point at its Own Game: Posit Arithmetic
Beating Floating Point at its Own Game: Posit Arithmeticinside-BigData.com
 
Deep learning simplified
Deep learning simplifiedDeep learning simplified
Deep learning simplifiedLovelyn Rose
 
Finding needles in haystacks with deep neural networks
Finding needles in haystacks with deep neural networksFinding needles in haystacks with deep neural networks
Finding needles in haystacks with deep neural networksCalvin Giles
 
Analysis of local affine model v2
Analysis of  local affine model v2Analysis of  local affine model v2
Analysis of local affine model v2cindy071434
 
Analysis of local affine model v2
Analysis of  local affine model v2Analysis of  local affine model v2
Analysis of local affine model v2cindy071434
 
DeepXplore: Automated Whitebox Testing of Deep Learning
DeepXplore: Automated Whitebox Testing of Deep LearningDeepXplore: Automated Whitebox Testing of Deep Learning
DeepXplore: Automated Whitebox Testing of Deep LearningMasahiro Sakai
 
Basics in algorithms and data structure
Basics in algorithms and data structure Basics in algorithms and data structure
Basics in algorithms and data structure Eman magdy
 
writing self-modifying code and utilizing advanced assembly techniques
writing self-modifying code and utilizing advanced assembly techniqueswriting self-modifying code and utilizing advanced assembly techniques
writing self-modifying code and utilizing advanced assembly techniquesRussell Sanford
 
Thai Text processing by Transfer Learning using Transformer (Bert)
Thai Text processing by Transfer Learning using Transformer (Bert)Thai Text processing by Transfer Learning using Transformer (Bert)
Thai Text processing by Transfer Learning using Transformer (Bert)Kobkrit Viriyayudhakorn
 

Similar to Deep Learning and Design Thinking (20)

Exact Real Arithmetic for Tcl
Exact Real Arithmetic for TclExact Real Arithmetic for Tcl
Exact Real Arithmetic for Tcl
 
Machine Learning on Azure - AzureConf
Machine Learning on Azure - AzureConfMachine Learning on Azure - AzureConf
Machine Learning on Azure - AzureConf
 
Gmat
GmatGmat
Gmat
 
Understanding Basics of Machine Learning
Understanding Basics of Machine LearningUnderstanding Basics of Machine Learning
Understanding Basics of Machine Learning
 
Cynthia Lee ITEM 2018
Cynthia Lee ITEM 2018Cynthia Lee ITEM 2018
Cynthia Lee ITEM 2018
 
How to Explain Post-Quantum Cryptography to a Middle School Student - Klaus S...
How to Explain Post-Quantum Cryptography to a Middle School Student - Klaus S...How to Explain Post-Quantum Cryptography to a Middle School Student - Klaus S...
How to Explain Post-Quantum Cryptography to a Middle School Student - Klaus S...
 
20190417 畳み込みニューラル ネットワークの基礎と応用
20190417 畳み込みニューラル ネットワークの基礎と応用20190417 畳み込みニューラル ネットワークの基礎と応用
20190417 畳み込みニューラル ネットワークの基礎と応用
 
The Attractor
The AttractorThe Attractor
The Attractor
 
Neural networks - BigSkyDevCon
Neural networks - BigSkyDevConNeural networks - BigSkyDevCon
Neural networks - BigSkyDevCon
 
Beating Floating Point at its Own Game: Posit Arithmetic
Beating Floating Point at its Own Game: Posit ArithmeticBeating Floating Point at its Own Game: Posit Arithmetic
Beating Floating Point at its Own Game: Posit Arithmetic
 
Deep learning simplified
Deep learning simplifiedDeep learning simplified
Deep learning simplified
 
Finding needles in haystacks with deep neural networks
Finding needles in haystacks with deep neural networksFinding needles in haystacks with deep neural networks
Finding needles in haystacks with deep neural networks
 
04 - 15 Jan - Heap Sort
04 - 15 Jan - Heap Sort04 - 15 Jan - Heap Sort
04 - 15 Jan - Heap Sort
 
04 - 15 Jan - Heap Sort
04 - 15 Jan - Heap Sort04 - 15 Jan - Heap Sort
04 - 15 Jan - Heap Sort
 
Analysis of local affine model v2
Analysis of  local affine model v2Analysis of  local affine model v2
Analysis of local affine model v2
 
Analysis of local affine model v2
Analysis of  local affine model v2Analysis of  local affine model v2
Analysis of local affine model v2
 
DeepXplore: Automated Whitebox Testing of Deep Learning
DeepXplore: Automated Whitebox Testing of Deep LearningDeepXplore: Automated Whitebox Testing of Deep Learning
DeepXplore: Automated Whitebox Testing of Deep Learning
 
Basics in algorithms and data structure
Basics in algorithms and data structure Basics in algorithms and data structure
Basics in algorithms and data structure
 
writing self-modifying code and utilizing advanced assembly techniques
writing self-modifying code and utilizing advanced assembly techniqueswriting self-modifying code and utilizing advanced assembly techniques
writing self-modifying code and utilizing advanced assembly techniques
 
Thai Text processing by Transfer Learning using Transformer (Bert)
Thai Text processing by Transfer Learning using Transformer (Bert)Thai Text processing by Transfer Learning using Transformer (Bert)
Thai Text processing by Transfer Learning using Transformer (Bert)
 

More from Yen-lung Tsai

強化學習 Reinforcement Learning
強化學習 Reinforcement Learning強化學習 Reinforcement Learning
強化學習 Reinforcement LearningYen-lung Tsai
 
生成對抗模式 GAN 的介紹
生成對抗模式 GAN 的介紹生成對抗模式 GAN 的介紹
生成對抗模式 GAN 的介紹Yen-lung Tsai
 
Recurrent Neural Network 遞迴式神經網路
Recurrent Neural Network 遞迴式神經網路Recurrent Neural Network 遞迴式神經網路
Recurrent Neural Network 遞迴式神經網路Yen-lung Tsai
 
手把手打開Python資料分析大門
手把手打開Python資料分析大門手把手打開Python資料分析大門
手把手打開Python資料分析大門Yen-lung Tsai
 
與高中生談人工智慧與深度學習
與高中生談人工智慧與深度學習與高中生談人工智慧與深度學習
與高中生談人工智慧與深度學習Yen-lung Tsai
 
深度學習實作上的各種卡關
深度學習實作上的各種卡關深度學習實作上的各種卡關
深度學習實作上的各種卡關Yen-lung Tsai
 
人工智慧不是魔法,是數學
人工智慧不是魔法,是數學人工智慧不是魔法,是數學
人工智慧不是魔法,是數學Yen-lung Tsai
 
[數學、邏輯與人生] 05 數,三聲數
[數學、邏輯與人生] 05 數,三聲數[數學、邏輯與人生] 05 數,三聲數
[數學、邏輯與人生] 05 數,三聲數Yen-lung Tsai
 
[數學軟體應用] 05 HTML+CSS
[數學軟體應用] 05 HTML+CSS[數學軟體應用] 05 HTML+CSS
[數學軟體應用] 05 HTML+CSSYen-lung Tsai
 
[數學、邏輯與人生] 03 集合和數學歸納法
[數學、邏輯與人生] 03 集合和數學歸納法[數學、邏輯與人生] 03 集合和數學歸納法
[數學、邏輯與人生] 03 集合和數學歸納法Yen-lung Tsai
 
[數學、邏輯與人生] 01 基本邏輯和真值表
[數學、邏輯與人生] 01 基本邏輯和真值表[數學、邏輯與人生] 01 基本邏輯和真值表
[數學、邏輯與人生] 01 基本邏輯和真值表Yen-lung Tsai
 
03 串起你的數據
03 串起你的數據03 串起你的數據
03 串起你的數據Yen-lung Tsai
 
Markdown可以做什麼
Markdown可以做什麼Markdown可以做什麼
Markdown可以做什麼Yen-lung Tsai
 
01 jupyter 第一課
01 jupyter 第一課01 jupyter 第一課
01 jupyter 第一課Yen-lung Tsai
 
[數學、邏輯與人生] 00 課程簡介
[數學、邏輯與人生] 00 課程簡介[數學、邏輯與人生] 00 課程簡介
[數學、邏輯與人生] 00 課程簡介Yen-lung Tsai
 
數學軟體應用課程 00 - 課程介紹
數學軟體應用課程 00 - 課程介紹數學軟體應用課程 00 - 課程介紹
數學軟體應用課程 00 - 課程介紹Yen-lung Tsai
 
用 GeoGebra 玩數學
用 GeoGebra 玩數學用 GeoGebra 玩數學
用 GeoGebra 玩數學Yen-lung Tsai
 

More from Yen-lung Tsai (19)

強化學習 Reinforcement Learning
強化學習 Reinforcement Learning強化學習 Reinforcement Learning
強化學習 Reinforcement Learning
 
生成對抗模式 GAN 的介紹
生成對抗模式 GAN 的介紹生成對抗模式 GAN 的介紹
生成對抗模式 GAN 的介紹
 
Recurrent Neural Network 遞迴式神經網路
Recurrent Neural Network 遞迴式神經網路Recurrent Neural Network 遞迴式神經網路
Recurrent Neural Network 遞迴式神經網路
 
手把手打開Python資料分析大門
手把手打開Python資料分析大門手把手打開Python資料分析大門
手把手打開Python資料分析大門
 
與高中生談人工智慧與深度學習
與高中生談人工智慧與深度學習與高中生談人工智慧與深度學習
與高中生談人工智慧與深度學習
 
深度學習實作上的各種卡關
深度學習實作上的各種卡關深度學習實作上的各種卡關
深度學習實作上的各種卡關
 
人工智慧不是魔法,是數學
人工智慧不是魔法,是數學人工智慧不是魔法,是數學
人工智慧不是魔法,是數學
 
[數學、邏輯與人生] 05 數,三聲數
[數學、邏輯與人生] 05 數,三聲數[數學、邏輯與人生] 05 數,三聲數
[數學、邏輯與人生] 05 數,三聲數
 
[數學軟體應用] 05 HTML+CSS
[數學軟體應用] 05 HTML+CSS[數學軟體應用] 05 HTML+CSS
[數學軟體應用] 05 HTML+CSS
 
[數學、邏輯與人生] 03 集合和數學歸納法
[數學、邏輯與人生] 03 集合和數學歸納法[數學、邏輯與人生] 03 集合和數學歸納法
[數學、邏輯與人生] 03 集合和數學歸納法
 
[數學、邏輯與人生] 01 基本邏輯和真值表
[數學、邏輯與人生] 01 基本邏輯和真值表[數學、邏輯與人生] 01 基本邏輯和真值表
[數學、邏輯與人生] 01 基本邏輯和真值表
 
03 串起你的數據
03 串起你的數據03 串起你的數據
03 串起你的數據
 
Markdown可以做什麼
Markdown可以做什麼Markdown可以做什麼
Markdown可以做什麼
 
02 和電腦對話
02 和電腦對話02 和電腦對話
02 和電腦對話
 
01 jupyter 第一課
01 jupyter 第一課01 jupyter 第一課
01 jupyter 第一課
 
[數學、邏輯與人生] 00 課程簡介
[數學、邏輯與人生] 00 課程簡介[數學、邏輯與人生] 00 課程簡介
[數學、邏輯與人生] 00 課程簡介
 
數學軟體應用課程 00 - 課程介紹
數學軟體應用課程 00 - 課程介紹數學軟體應用課程 00 - 課程介紹
數學軟體應用課程 00 - 課程介紹
 
Days on Jupyter
Days on JupyterDays on Jupyter
Days on Jupyter
 
用 GeoGebra 玩數學
用 GeoGebra 玩數學用 GeoGebra 玩數學
用 GeoGebra 玩數學
 

Recently uploaded

How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 

Recently uploaded (20)

How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 

Deep Learning and Design Thinking