1.
Introduction to Deep Learning
UCSC Meetup (Santa Clara)
Monday 08/12/2019
Oswald Campesato
ocampesato@yahoo.com

2.
High-Level List of Topics
intro to AI/ML/DL/ANNs
Hidden layers/Initialization/Neurons per layer
Activation function
cost function/gradient descent/learning rate
Dropout rate
What is linear regression
what are CNNs

3.
Topics We Won’t Cover
RNNs, LSTMs, and VAEs
Transformers et al
Reinforcement Learning (RL)
Deep Reinforcement Learning (DRL)
Natural Language Processing (NLP)

4.
The Data/AI Landscape

5.
The Official Start of AI (1956)

6.
Use Cases for Deep Learning
computer vision
speech recognition
image processing
bioinformatics
social network filtering
drug design
Customer relationship management
Recommendation systems
Bioinformatics
Mobile Advertising
Many others

7.
What is a Deep Neural Network?
 input layer, multiple hidden layers, and output layer
 nonlinear processing via activation functions
 perform transformation and feature extraction
 gradient descent algorithm with back propagation
 each layer receives the output from previous layer
 results are comparable/superior to human experts

8.
Types of Deep Learning
 Supervised learning (you know the answer)
 unsupervised learning (you don’t know the answer)
 Semi-supervised learning (mixed dataset)
 Reinforcement learning (such as games)
 Types of algorithms:
 Classifiers (detect images, spam, fraud, etc)
 Regression (predict stock price, housing price, etc)
 Clustering (unsupervised classifiers)

9.
Deep Learning Architectures
Unsupervised Pre-trained Networks (UPNs)
Convolutional Neural Networks (CNNs)
Recurrent Neural Networks (LSTMs)
The most popular architectures:
CNNs (and capsule networks) for images
LSTMs for NLP and audio

10.
Neural Network: 3 Hidden Layers

11.
NN: 2 Hidden Layers (Regression)

12.
Titanic Dataset (portion)

13.
Classification and Deep Learning

14.
What is 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: = minimize sum of squared values
b also has a closed form solution

15.
Linear Regression in 2D: example

16.
Linear Regression in 2D: example

17.
Sample Cost Function #1 (MSE)

18.
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

19.
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)

20.
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

21.
Neural Network with 3 Hidden Layers

22.
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

23.
Euler’s Function (e: 2.71828. . .)

24.
The sigmoid Activation Function

25.
The tanh Activation Function

26.
The ReLU Activation Function

27.
The softmax Activation Function

28.
Gaussian Functions

29.
Gaussian Functions

30.
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))

31.
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

32.
Types of Cost/Error Functions
MSE (mean-squared error)
Cross-entropy
others

33.
Sample Cost Function #1 (MSE)

34.
Sample Cost Function #2

35.
Sample Cost Function #3

36.
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

37.
Types of Optimizers
SGD
rmsprop
Adagrad
Adam
Others
http://cs229.stanford.edu/notes/cs229-notes1.pdf

38.
Setting up Data & the Model
standardize 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

39.
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

40.
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

41.
How Many Layers in a DNN?
Algorithm #1 (from Geoffrey Hinton):
1) add layers until you start overfitting your
training set
2) now add dropout or some another
regularization method
Algorithm #2 (Yoshua Bengio):
"Add layers until the test error does not improve
anymore.”

42.
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

43.
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
Used in hybrid networks

44.
CNNs: Convolution, ReLU, and Max Pooling

45.
CNNs: Convolution Calculations
https://docs.gimp.org/en/plug-in-convmatrix.html

46.
CNNs: Convolution Matrices (examples)
Sharpen:
Blur:

47.
CNNs: Convolution Matrices (examples)
Edge detect:
Emboss:

48.
CNNs: Convolution Matrices (examples)

49.
CNNs: Convolution Matrices (examples)

50.
CNNs: Convolution Matrices (examples)

51.
CNN Filter Terminology
Stride:
how many units you “shift” the filter (1/2/3/etc)
Padding:
makes feature map same size as image
Kernel size:
the dimensions of the filter (1x1, 3x3, 5x5, etc)

52.
CNNs: Max Pooling Example

53.
Components of a CNN (again)
1) Specify the input layer
2) Add a convolution to create feature maps
3) Perform RELU on the feature maps
4) repeat 1) and 2)
5) add a FC (fully connected layer)
6) connect FC to output layer via softmax

54.
CNN pseudocode
 Specify an optimiser
 specify a cost function
 specify a learning rate
 Specify desired metrics (accuracy/precision/etc)
 specify # of batch runs in a training epoch
 For each epoch:
 For each batch:
 Extract the batch data
 Run the optimiser + cross-entropy operations
 Add to the average cost
 Calculate the current test accuracy
 Print out some results
 Calculate the final test accuracy and print

55.
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))

56.
GANs: Generative Adversarial Networks

57.
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

58.
GANs: Generative Adversarial Networks
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 and Capsule networks?

59.
What is TensorFlow 2?
 Support for Python, Java, C++
 Desktop, Server, Mobile, Web
 CPU/GPU/TPU support
 Visualization via TensorBoard
 Can be embedded in Python scripts
 Installation: pip install tensorflow
 Ex: pip install tensorflow==2.0.0-beta1

60.
TensorFlow Use Cases (Generic)
Image recognition
Computer vision
Voice/sound recognition
Time series analysis
Language detection
Language translation
Text-based processing
Handwriting Recognition

61.
Major Changes in TF 2
 TF 2 Eager Execution: default mode
 @tf.function decorator: instead of tf.Session()
 AutoGraph: graph generated in @tf.function()
 Generators: used with tf.data.Dataset (TF 2)
 Differentiation: calculates gradients
 tf.GradientTape: automatic differentiation

62.
Removed from TensorFlow 2
 tf.Session()
 tf.placeholder()
 tf.global_initializer()
 feed_dict
 Variable scopes
 tf.contrib code
 tf.flags and tf.contrib
 Global variables
 => TF 1.x functions moved to compat.v1

63.
Deep Learning and Art/”Stuff”
“Convolutional Blending” images:
=> 19-layer Convolutional Neural Network
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

64.
Upcoming Classes at UCSC

65.
About Me: Recent Books
 1) Angular and Machine Learning (2020)
 2) Angular and Deep Learning (2020)
 3) AI/ML/DL: Concepts and Code (2020)
 4) Shell Programming in Bash (2020)
 5) TensorFlow 2 Pocket Primer (2019)
 6) TensorFlow 1.x Pocket Primer (2019)
 7) Python for TensorFlow (2019)
 8) C Programming Pocket Primer (2019)
 9) RegEx Pocket Primer (2018)
 10) Data Cleaning Pocket Primer (2018)
 11) Angular Pocket Primer (2017)
 12) Android Pocket Primer (2017)
 13) CSS3 Pocket Primer (2016)

66.
About Me: Less Recent Books
 14) SVG Pocket Primer (2016)
 15) Python Pocket Primer (2015)
 16) D3 Pocket Primer (2015)
 17) HTML5 Mobile Pocket Primer (2014)
 18) jQuery, CSS3, and HTML5 (2013)
 19) HTML5 Pocket Primer (2013)
 20) jQuery Pocket Primer (2013)
 21) HTML5 Canvas (2012)
 22) Flash on Android (2011)
 23) Web 2.0 Fundamentals (2010)
 24) MS Silverlight Graphics (2008)
 25) Fundamentals of SVG (2003)
 26) Java Graphics Library (2002)