This document provides information about Marwa Ayad Mohamed and her presentation on machine learning with Google tools. It discusses artificial intelligence, machine learning, deep learning, and how these concepts are used for applications like image recognition, object recognition, smart email reply, voice recognition, self-driving cars, and more. It then describes TensorFlow, a popular machine learning library developed by Google, how the programming model works, and provides steps for installing TensorFlow and running demos like image recognition on Windows systems. Contact information is also included at the end.
"Exploring the Essential Functions and Design Considerations of Spillways in ...
2017 arab wic marwa ayad machine learning
1. Marwa Ayad Mohmed
Team Lead Software Engineer
WTM/GDG
Engmarwaayad@gmail.com || @ayad_marwa
2017 ArabWIC Conference on Arab Women in Computing
Machine Learning with Google Tools
2.
3. Marwa Ayad Mohamed
• WTM lead Cairo.
• +8 year experience in software
field.
• Graduation Faculty of Engineering
Ain Shams University.
• Master Degree “Cloud Computing
and CPU, GPU integration”.
• Researcher in Machine Learning.
• Public Speaker and Project
monitor.
• Founder of YourChildCode.
6. ArtificialIntelligence
• AI or artificial intelligence : is the simulation of human
intelligence processes by machines, especially
computer systems.
• These processes include learning (the information
and rules for using the information).
• reasoning (using the rules to reach approximate or
definite conclusions).
7. Machine learning
• Machine learning is a type of artificial intelligence (AI)
that provides computers with the ability to learn
without being explicitly programmed.
• Machine learning focuses on
the development of computer
programs that can change
when exposed to new data.
8. Machine learning
• Supervised learning
• Unsupervised learning
• Machine learning technics that use multiple learning
algorithm to have the applet to extract the useful
information from input data.
• Machine learning involves machines self-developing
models to process data and make predictions
10. Deep Learning
• Deep Learning is a new area of Machine Learning
research, which has been introduced with the
objective of moving Machine Learning closer to one of
its original goals
• that is concerned with emulating the learning
approach that human beings use to gain certain types
of knowledge.
23. TensorFlow
• TensorFlow™ is an open source software library for
numerical computation and machine learning.
• Especially useful for Deep learning
• For research and production
• Developed by Google Brain Team
24. TensorFlow Story
• TensorFlow was originally developed by researchers and
engineers working on the Google Brain Team within
Google's Machine Intelligence research organization for
the purposes of conducting machine learning and deep
neural networks research.
• Most Most popular machine learning library.
o Over 32,000 downlowds
25. Tensorflow Model
• Big idea: Express a numeric computation as a graph.
• Nodes = Mathematical Operations
o Nodes in the graph represent mathematical operations,
• Data Edges = Multi-Dimensional Arrays
(Tensor)
o communicated between them
• Data (Tensors) flow through the graph
26. Data flow graphs
• Computation is defined
as directed a cyclic graph (GDA)
o Optimize an objective function.
• Graph is defined in high-level
Language (python, C++,Go)
• Graph is compiled and optimized
• Graph is executed (parts or fully)
On level devices (CPU, GPU).
27. Architecture
• Core in C++
• Front end code python and C++.
• The flexible architecture allows you to deploy
computation to one or more CPUs or GPUs
28. Portable & scalable
• deploy computation in a desktop, server, or mobile
device with a single API
31. Programming model
(Build a graph)
• Variables are 0-ary stateful
nodes which output their
current value.
• Placeholders are 0-ary
nodes whose value is fed in at
execution time.
• Mathematical operations:
o MatMul: Multiply two matrix
values.
o Add: Add elementwise (with
broadcasting).
o ReLU: Activate with elementwise
rectified linear function.
32. Programming model
(Build a graph)
• import tensorflow as tf
b = tf.Variable(tf.zeros((100,)))
W=tf.Variable(tf.random_uniform((784,
100), -1, 1))
x = tf.placeholder(tf.float32, (None,
784))
h_i = tf.nn.relu(tf.matmul(x, W) + b)
33. Programming model
(Initialize & Run session)
• a session: a binding to a particular execution context
sess.run(fetches, feeds)
Fetches: List of graph nodes. Return the outputs of these
nodes.
Feeds: Dictionary mapping from graph nodes to concrete
values. Specifies the value of each graph node given in
the dictionary.
34. Programming model
(Build a graph)
import numpy as np
import tensorflow as tf
b = tf.Variable(tf.zeros((100,)))
W = tf.Variable(tf.random_uniform((784, 100),
-1, 1))
x = tf.placeholder(tf.float32, (None, 784))
h_i = tf.nn.relu(tf.matmul(x, W) + b)
-----Initial and Run Session-------
sess = tf.Session()
sess.run(tf.initialize_all_variables())
sess.run(h_i, {x: np.random.random(64, 784)})
36. Software tools requirement
and Steps
• Software tools requirement
o Python 3.5.x.
o Microsoft Visual C++ 2015 Redistributable.
• Installing python
• Installing TensorFlow on Windows
• Hello, TensorFlow!
• TensorFlow Image Recognition Demo
37. Installing TensorFlow on Windows
• Determine which TensorFlow to install.
o TensorFlow with CPU support only. If your system does not
have a NVIDIA® GPU
o TensorFlow with GPU support.
• the mechanism by which you install TensorFlow.
o "native" pip (Recommended )
• Native pip installs TensorFlow directly on your system without going
through a virtual environment.
o Anaconda (not officially supported)
• you may use conda to create a virtual environment.
• https://www.tensorflow.org/install/install_windows
39. Validate your installation
(Hello, TensorFlow!)
1. Start a terminal.
2. Inside that terminal, invoke python:
o C:> python
3. Enter the following short program inside the python
interactive shell:
>>> import tensorflow as tf
>>> hello = tf.constant('Hello, TensorFlow!')
>>> sess = tf.Session()
>>> print(sess.run(hello))
4. Hello, TensorFlow!
41. Image Recognition
DEMO
• We're now taking the next step by releasing code for
running image recognition on our latest model, Inception-
v3.
• Inception-v3 is trained for the ImageNet Large Visual
Recognition Challenge using the data from 2012.
• The models try to classify entire images into 1000
classes,
like "Zebra", "Dalmatian", and "Dishwasher".
44. Image Recognition
DEMO
• If you wish to supply other JPEG images, you may do so
by editing the --image_fileargument.
• If you download the model data to a different directory,
you will need to point --model_dir to the directory used.