Deep Learning, Keras, and TensorFlow

Introduction to Deep Learning, Keras,
and TensorFlow
H2O Meetup 03/13/2018 MTV
Oswald Campesato
oswald@perceptrons.io
http://perceptrons.io

Highlights/Overview
intro to AI/ML/DL
linear regression
activation/cost functions
gradient descent
back propagation
hyper-parameters
what are CNNs
What is Keras?
What is TensorFlow?

Gartner 2017: Deep Learning (YES!)

The Official Start of AI (1956)

Neural Network with 3 Hidden Layers

Linear Classifier: Example #1
Given some red dots and blue dots
Red dots are in the upper half plane
Blue dots in the lower half plane
How to detect if a point is red or blue?

Given some red dots and blue dots
Red dots are inside a unit square
Blue dots are outside the unit square
How to detect if a point is red or blue?

 Two input nodes X and Y
 One hidden layer with 4 nodes (one per line)
 X & Y weights are the (x,y) values of the inward pointing
perpendicular vector of each side
 The threshold values are the negative of the y-intercept
(or the x-intercept)
 The outbound weights are all equal to 1
 The threshold for the output node node is 4

Exercises #1
Describe an NN for a triangle
Describe an NN for a pentagon
Describe an NN for an n-gon (convex)
Describe an NN for an n-gon (non-convex)

Exercises #2
Create an NN for an OR gate
Create an NN for a NOR gate
Create an NN for an AND gate
Create an NN for a NAND gate
Create an NN for an XOR gate
=> requires TWO hidden layers

Exercises #3
Convert example #2 to a 3D cube

A few points to keep in mind:
A “step” activation function (0 or 1)
No back propagation
No cost function
=> no learning involved

A Basic Model in Machine Learning
Let’s perform the following steps:
1) Start with a simple model (2 variables)
2) Generalize that model (n variables)
3) See how it might apply to a NN

Linear Regression
One of the simplest models in ML
Fits a line (y = m*x + b) to data in 2D
Finds best line by minimizing MSE:
m = average of x values (“mean”)
b also has a closed form solution

Linear Regression in 2D: example

Linear Regression: example #1
One feature (independent variable):
X = number of square feet
Predicted value (dependent variable):
Y = cost of a house
A very “coarse grained” model
We can devise a much better model

Linear Regression: example #2
Multiple features:
X1 = # of square feet
X2 = # of bedrooms
X3 = # of bathrooms (dependency?)
X4 = age of house
X5 = cost of nearby houses
X6 = corner lot (or not): Boolean
a much better model (6 features)

Linear Multivariate Analysis
General form of multivariate equation:
Y = w1*x1 + w2*x2 + . . . + wn*xn + b
w1, w2, . . . , wn are numeric values
x1, x2, . . . , xn are variables (features)
Properties of variables:
Can be independent (Naïve Bayes)
weak/strong dependencies can exist

Neural Networks: equations
Node “values” in first hidden layer:
N1 = w11*x1+w21*x2+…+wn1*xn
N2 = w12*x1+w22*x2+…+wn2*xn
N3 = w13*x1+w23*x2+…+wn3*xn
. . .
Nn = w1n*x1+w2n*x2+…+wnn*xn
Similar equations for other pairs of layers

Neural Networks: Matrices
From inputs to first hidden layer:
Y1 = W1*X + B1 (X/Y1/B1: vectors; W1: matrix)
From first to second hidden layers:
From second to third hidden layers:
 Apply an “activation function” to y values

Neural Networks (general)
Multiple hidden layers:
Layer composition is your decision
Activation functions: sigmoid, tanh, RELU
https://en.wikipedia.org/wiki/Activation_function
Back propagation (1980s)
https://en.wikipedia.org/wiki/Backpropagation
=> Initial weights: small random numbers

The sigmoid Activation Function

The softmax Activation Function

Activation Functions in Python
import numpy as np
...
# Python sigmoid example:
z = 1/(1 + np.exp(-np.dot(W, x)))
...
# Python tanh example:
z = np.tanh(np.dot(W,x));
# Python ReLU example:
z = np.maximum(0, np.dot(W, x))

What’s the “Best” Activation Function?
Initially: sigmoid was popular
Then: tanh became popular
Now: RELU is preferred (better results)
Softmax: for FC (fully connected) layers
NB: sigmoid and tanh are used in LSTMs

How to Select a Cost Function
mean-squared error:
for a regression problem
binary cross-entropy (or mse):
for a two-class classification problem
categorical cross-entropy:
for a many-class classification problem

Setting up Data & the Model
Normalize the data:
Subtract the ‘mean’ and divide by stddev
Initial weight values for NNs:
random(0,1) or N(0,1) or N(0/(1/n))
More details:
http://cs231n.github.io/neural-networks-2/#losses

Hyper Parameters (examples)
# of hidden layers in a neural network
the learning rate (in many models)
the dropout rate
# of leaves or depth of a tree
# of latent factors in a matrix factorization
# of clusters in a k-means clustering

Hyper Parameter: dropout rate
"dropout" refers to dropping out units (both hidden
and visible) in a neural network
a regularization technique for reducing overfitting in
neural networks
prevents complex co-adaptations on training data
a very efficient way of performing model averaging
with neural networks

How Many Hidden Nodes in a DNN?
Based on a relationship between:
# of input and # of output nodes
Amount of training data available
Complexity of the cost function
The training algorithm
TF playground home page:
http://playground.tensorflow.org

CNNs versus RNNs
CNNs (Convolutional NNs):
Good for image processing
2000: CNNs processed 10-20% of all checks
=> Approximately 60% of all NNs
RNNs (Recurrent NNs):
Good for NLP and audio

CNNs: convolution and pooling (2)

CNNs: Convolution Calculations
https://docs.gimp.org/en/plug-in-convmatrix.html

CNNs: Convolution Matrices (examples)
Sharpen:
Blur:

CNNs: Convolution Matrices (examples)
Edge detect:
Emboss:

What is Keras?
a high-level NN API
written in Python
supports TensorFlow and CNTK
supports CNNs and RNNs
supports CPUs and GPUs
good for prototyping
https://keras.io/

Basic Keras Example
from keras.models import Sequential
from keras.layers import Dense, Activation
model = Sequential([
 Dense(32, input_shape=(784,)),
 Activation('relu'),
 Dense(10),
 Activation('softmax'),
])
model.summary()

Basic Keras Example
 Using TensorFlow backend.
 ___________________________________________________________
______
 Layer (type) Output Shape Param #
 ======================================================
===========
 dense_1 (Dense) (None, 32) 25120
 ___________________________________________________________
______
 activation_1 (Activation) (None, 32) 0
 ___________________________________________________________
______
 dense_2 (Dense) (None, 10) 330
 ___________________________________________________________
______
 activation_2 (Activation) (None, 10) 0
 ======================================================
===========
 Total params: 25,450
 Trainable params: 25,450

CNN in Python/Keras (fragment)
 from keras.models import Sequential
 from keras.layers.core import Dense, Dropout, Flatten, Activation
 from keras.layers.convolutional import Conv2D, MaxPooling2D
 from keras.optimizers import Adadelta
 input_shape = (3, 32, 32)
 nb_classes = 10
 model = Sequential()
 model.add(Conv2D(32, (3, 3), padding='same’,
input_shape=input_shape))
 model.add(Activation('relu'))
 model.add(Conv2D(32, (3, 3)))
 model.add(Activation('relu'))
 model.add(MaxPooling2D(pool_size=(2, 2)))
 model.add(Dropout(0.25))

What is TensorFlow?
An open source framework for ML and DL
A “computation” graph
Created by Google (released 11/2015)
Evolved from Google Brain
Linux and Mac OS X support (VM for Windows)
TF home page: https://www.tensorflow.org/

What is TensorFlow?
Support for Python, Java, C++
Desktop, server, mobile device (TensorFlow Lite)
CPU/GPU/TPU support
Visualization via TensorBoard
Can be embedded in Python scripts
Installation: pip install tensorflow
TensorFlow cluster:
https://www.tensorflow.org/deploy/distributed

TensorFlow Use Cases (Generic)
Image recognition
Computer vision
Voice/sound recognition
Time series analysis
Language detection
Language translation
Text-based processing
Handwriting Recognition

What is TensorFlow?
Graph: graph of operations (DAG)
Sessions: contains Graph(s)
lazy execution (default)
operations in parallel (default)
Nodes: operators/variables/constants
Edges: tensors
=> graphs are split into subgraphs and
executed in parallel (or multiple CPUs)

TensorFlow Graph Execution
Execute statements in a tf.Session() object
Invoke the “run” method of that object
“eager” execution is now possible
Not part of the mainline yet
Installation: pip install tf-nightly

What is a Tensor?
TF tensors are n-dimensional arrays
TF tensors are very similar to numpy ndarrays
scalar number: a zeroth-order tensor
vector: a first-order tensor
matrix: a second-order tensor
3-dimensional array: a 3rd order tensor
https://dzone.com/articles/tensorflow-simplified-
examples

TensorFlow “primitive types”
 tf.constant: initialized immediately
 tf.placeholder (a function):
+ initial value is not required
+ assigned value via feed_dict at run time
+ are not modified during training
 tf.Variable (a class):
+ initial value is required
+ updated during training
+ in-memory buffer (saved/restored from disk)
+ can be shared between works (distributed env)

TensorFlow: constants (immutable)
 import tensorflow as tf # tf-const.py
 aconst = tf.constant(3.0)
 print(aconst)
# output: Tensor("Const:0", shape=(), dtype=float32)
 sess = tf.Session()
 print(sess.run(aconst))
# output: 3.0
 sess.close()
 # => there's a better way…

TensorFlow: constants
import tensorflow as tf # tf-const2.py
aconst = tf.constant(3.0)
print(aconst)
Automatically close “sess”
with tf.Session() as sess:
 print(sess.run(aconst))

TensorFlow Arithmetic
import tensorflow as tf # basic1.py
a = tf.add(4, 2)
b = tf.subtract(8, 6)
c = tf.multiply(a, 3)
d = tf.div(a, 6)
with tf.Session() as sess:
print(sess.run(a)) # 6
print(sess.run(b)) # 2
print(sess.run(c)) # 18
print(sess.run(d)) # 1

TensorFlow Arithmetic Methods
import tensorflow as tf #tf-math-ops.py
PI = 3.141592
sess = tf.Session()
print(sess.run(tf.div(12,8)))
print(sess.run(tf.floordiv(20.0,8.0)))
print(sess.run(tf.sin(PI)))
print(sess.run(tf.cos(PI)))
print(sess.run(tf.div(tf.sin(PI/4.), tf.cos(PI/4.))))

TensorFlow Arithmetic Methods
Output from tf-math-ops.py:
1
2.0
6.27833e-07
-1.0
1.0

TF placeholders and feed_dict
import tensorflow as tf # tf-var-multiply.py
a = tf.placeholder("float")
b = tf.placeholder("float")
c = tf.multiply(a,b)
# initialize a and b:
feed_dict = {a:2, b:3}
# multiply a and b:
print(sess.run(c, feed_dict))

TensorFlow and Linear Regression
import tensorflow as tf
# W and x are 1d arrays
W = tf.constant([10,20], name=’W’)
x = tf.placeholder(tf.int32, name='x')
b = tf.placeholder(tf.int32, name='b')
Wx = tf.multiply(W, x, name='Wx')
y = tf.add(Wx, b, name=’y’)

TensorFlow fetch/feed_dict
print("Result 1: Wx = ",
sess.run(Wx, feed_dict={x:[5,10]}))
print("Result 2: y = ",
sess.run(y, feed_dict={x:[5,10], b:[15,25]}))
Result 1: Wx = [50 200]
Result 2: y = [65 225]

Saving Graphs for TensorBoard
import tensorflow as tf # tf-save-data.py
x = tf.constant(5,name="x")
y = tf.constant(8,name="y")
z = tf.Variable(2*x+3*y, name="z”)
model = tf.global_variables_initializer()
with tf.Session() as session:
writer = tf.summary.FileWriter(”./tf_logs",session.graph)
session.run(model)
print 'z = ',session.run(z) # => z = 34
# launch tensorboard: tensorboard –logdir=./tf_logs

TensorFlow Eager Execution
An imperative interface to TF (experimental)
Fast debugging & immediate run-time errors
Eager execution is not included in v1.4 of TF
build TF from source or install the nightly build
pip install tf-nightly # CPU
pip install tf-nightly-gpu #GPU
=> requires Python 3.x (not Python 2.x)

integration with Python tools
Supports dynamic models + Python control flow
support for custom and higher-order gradients
Supports most TensorFlow operations
https://research.googleblog.com/2017/10/eager-
execution-imperative-define-by.html

import tensorflow as tf # tf-eager1.py
import tensorflow.contrib.eager as tfe
tfe.enable_eager_execution()
x = [[2.]]
m = tf.matmul(x, x)
print(m)
# tf.Tensor([[4.]], shape=(1, 1), dtype=float32)

TensorFlow and CNNs (#1)
 def cnn_model_fn(features, labels, mode): # input layer
 input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])
 conv1 = tf.layers.conv2d( # Conv layer #1
 inputs=input_layer,
 filters=32,
 kernel_size=[5,5],
 padding="same",
 activation=tf.nn.relu)
 # Pooling Layer #1
 pool1 = tf.layers.max_pooling2d(inputs=conv1,
pool_size=[2, 2], strides=2)

 # Conv Layer #2 and Pooling Layer #2
 conv2 = tf.layers.conv2d(
 inputs=pool1,
 filters=64,
 kernel_size=[5,5],
 padding="same",
 activation=tf.nn.relu)
 pool2 = tf.layers.max_pooling2d(inputs=conv2,
pool_size=[2, 2], strides=2)

Other code details:
dense layer
dropout rate
predictions
calculate loss
specify metrics
Complete code listing for TF CNN:
https://www.tensorflow.org/tutorials/layers

GANs: Generative Adversarial Networks

Make imperceptible changes to images
Can consistently defeat all NNs
Can have extremely high error rate
Some images create optical illusions
https://www.quora.com/What-are-the-pros-and-cons-
of-using-generative-adversarial-networks-a-type-of-
neural-network

Create your own GANs:
https://www.oreilly.com/learning/generative-adversarial-networks-for-
beginners
https://github.com/jonbruner/generative-adversarial-networks
GANs from MNIST:
http://edwardlib.org/tutorials/gan

 GANs, Graffiti, and Art:
https://thenewstack.io/camouflaged-graffiti-road-signs-can-fool-
machine-learning-models/
https://www.quora.com/What-are-some-of-the-ways-to-combat-
adversarial-attacks-on-neural-networks-and-improve-the-network-
robustness/answer/Jerry-Liu-10
GANs and audio:
https://www.technologyreview.com/s/608381/ai-shouldnt-believe-
everything-it-hears
Image recognition (single pixel change):
http://www.bbc.com/news/technology-41845878

Deep Learning and Art
“Convolutional Blending” (19-layer CNN):
www.deepart.io
Bots created their own language:
https://www.recode.net/2017/3/23/14962182/ai-learning-
language-open-ai-research
https://www.fastcodesign.com/90124942/this-google-
engineer-taught-an-algorithm-to-make-train-footage-
and-its-hypnotic

What Do I Learn Next?
 PGMs (Probabilistic Graphical Models)
 MC (Markov Chains)
 MCMC (Markov Chains Monte Carlo)
 HMMs (Hidden Markov Models)
 RL (Reinforcement Learning)
 Hopfield Nets
 Neural Turing Machines
 Autoencoders
 Hypernetworks
 Pixel Recurrent Neural Networks
 Bayesian Neural Networks
 SVMs

About Me: Recent Books
1) HTML5 Canvas and CSS3 Graphics (2013)
2) jQuery, CSS3, and HTML5 for Mobile (2013)
3) HTML5 Pocket Primer (2013)
4) jQuery Pocket Primer (2013)
5) HTML5 Mobile Pocket Primer (2014)
6) D3 Pocket Primer (2015)
7) Python Pocket Primer (2015)
8) SVG Pocket Primer (2016)
9) CSS3 Pocket Primer (2016)
10) Android Pocket Primer (2017)
11) Angular Pocket Primer (2017)
12) Data Cleaning Pocket Primer (2018)
13) RegEx Pocket Primer (2018)

About Me: Training
=> Deep Learning. Keras, and TensorFlow:
http://codeavision.io/training/deep-learning-workshop
=> Mobile and TensorFlow Lite (WIP)
=> R and Deep Learning (WIP)
=> Android for Beginners

Deep Learning, Keras, and TensorFlow

More Related Content

What's hot (20)

Similar to Deep Learning, Keras, and TensorFlow (20)

More from Oswald Campesato (10)

Recently uploaded (20)

Deep Learning, Keras, and TensorFlow