This presentation introduces Deep Learning (DL) concepts, such as neural neworks, backprop, activation functions, and Convolutional Neural Networks, followed by an Angular application that uses TypeScript in order to replicate the Tensorflow playground.
4. The Impact of AI
“Robot trucks will kill far fewer people (if any).
Machines don’t get distracted or look at phones
instead of the road.
Machines don’t drink alcohol, do drugs, or things that
contribute to accidents.”
Robot trucks don’t need salaries, vacations, health
insurance, rest periods, or sick time.
The only costs will be upkeep of the machinery.
5. AI/ML/DL: How They Differ
Traditional AI (20th century):
based on collections of rules
Led to expert systems in the 1980s
The era of LISP and Prolog
6. AI/ML/DL: How They Differ
Machine Learning:
Started in the 1950s (approximate)
Alan Turing and “learning machines”
Data-driven (not rule-based)
Many types of algorithms
Involves optimization
7. AI/ML/DL: How They Differ
Deep Learning:
Started in the 1950s (approximate)
The “perceptron” (basis of NNs)
Data-driven (not rule-based)
large (even massive) data sets
Involves neural networks (CNNs: ~1970s)
Lots of heuristics
Heavily based on empirical results
8. The Rise of Deep Learning
Massive and inexpensive computing power
Huge volumes of data/Powerful algorithms
The “big bang” in 2009:
”deep-learning neural networks and NVidia GPUs"
Google Brain used NVidia GPUs (2009)
9. AI/ML/DL: Commonality
All of them involve a model
A model represents a system
Goal: a good predictive model
The model is based on:
Many rules (for AI)
data and algorithms (for ML)
large sets of data (for DL)
10. 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
11. 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
13. Linear Regression: alternatives
Fitting a polynomial (degree 2, 3, …)
Can lead to overfitting
Polynomials diverge faster than lines
Can reduce predictive accuracy
NB: Linear Regression != Curve Fitting
14. 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
15. 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)
16. 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
18. 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
19. 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:
Y2 = W2*X + B2 (X/Y2/B2: vectors; W2: matrix)
From second to third hidden layers:
Y3 = W3*X + B3 (X/Y3/B3: vectors; W3: matrix)
Apply an “activation function” to y values
20. 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
22. What’s the “Best” Activation Function?
Initially sigmoid was popular
then tanh became popular
Now RELU is preferred (better results)
NB: sigmoid + tanh are used in LSTMs
25. How to Select a Cost Function
1) Depends on the learning type:
=> supervised/unsupervised/RL
2) Depends on the activation function
3) Other factors
Example:
cross-entropy cost function for supervised
learning on multiclass classification
26. GD versus SGD
SGD (Stochastic Gradient Descent):
+ involves a SUBSET of the dataset
+ aka Minibatch Stochastic Gradient Descent
GD (Gradient Descent):
+ involves the ENTIRE dataset
More details:
http://cs229.stanford.edu/notes/cs229-notes1.pdf
27. What are Hyper Parameters?
higher level concepts about the model such as
complexity, or capacity to learn
Cannot be learned directly from the data in the
standard model training process
must be predefined
28. Hyper Parameters (examples)
# of hidden layers in a neural network
the learning rate (in many models)
# of leaves or depth of a tree
# of latent factors in a matrix factorization
# of clusters in a k-means clustering
29. 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.”
30. 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
31. Use Cases for Neural Networks
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
35. Features of LSTMs
Used in Google speech recognition + Alpha Go
input/output/forget gates
they avoid the vanishing gradient problem
Can track 1000s of discrete time steps
Used by international competition winners
Often combined with CTC
41. 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
42. ML/DL Frameworks
Caffe (templates instead of code)
Theano (influenced TensorFlow)
Tensorflow
TensorFlow Lite (release date?)
Keras (“layer” over Theano+TF)
Tefla (mini framework over TF)
Torch (Lua) + PyTorch (Facebook)
MxNET (Amazon)
CNTK (Microsoft)
43. Languages for ML/DL
Popular languages for ML:
R (popular among statisticians)
Python (sklearn/pandas/etc)
Popular languages for DL:
Python (Keras/Theano/TF modules)
some Java/C++/Go
44. “Challenges” in Deep Learning
overfitting/underfitting of a model
vanishing/exploding gradient
learning rate (too high or too low)
Debugging NNs (good luck)
45. Miscellaneous Topics
* Data versus algorithms:
Option A: good data + average algorithm
Option B: average data + good algorithm
=> Option A is preferred over Option B
• “Cleaning” a dataset:
De-duplicate and fix invalid/missing data (how?)
* Dimensionality reduction:
eliminate “unimportant” features (columns)
46. Miscellaneous Topics
* XOR requires two hidden layers to solve (why?)
• A dataset whose columns are interchangeable cannot be
solved with a CNN (why?)
• Second generation TPUs
• TensorFlow Lite (open source later in 2017)
www.tensorflow.org/tutorials
47. D3 Fun Samples
D3 Animation effects:
MouseMoveFadeAnim1Back1.html
SVG tiger:
svg-tiger-d3.svg
D3 and SVG tiger:
svg-tiger-d3.html
48. Deep Learning Playground
TF playground home page:
http://playground.tensorflow.org
Demo #1:
https://github.com/tadashi-aikawa/typescript-
playground
Converts playground to TypeScript
50. D3/TypeScript/Deep Learning
TypeScript files in ‘src’ directory:
state.ts
seedrandom.d.ts
playground.ts
linechart.ts
heatmap.ts
dataset.ts
nn.ts (<= activations/nodes in a neural net)
51. Activations in TypeScript (nn.ts)
export class Activations {
public static TANH: ActivationFunction = {
output: x => (Math as any).tanh(x),
der: x => {
let output = Activations.TANH.output(x);
return 1 - output * output;
}
};
public static RELU: ActivationFunction = {
output: x => Math.max(0, x),
der: x => x <= 0 ? 0 : 1
};
52. Activations in TypeScript (nn.ts)
public static SIGMOID: ActivationFunction = {
output: x => 1 / (1 + Math.exp(-x)),
der: x => {
let output = Activations.SIGMOID.output(x);
return output * (1 - output);
}
};
public static LINEAR: ActivationFunction = {
output: x => x,
der: x => 1
};
}
53. Angular/Deep Learning App (Demo #2)
Create NGDeepLearning via ‘ng’
Copy ./src/*ts files from playground_master into
NGDeepLearning/src subdirectory
Merge the two package.json files
Merge the two index.html files
install d3: npm install d3 --save
54. Angular/Deep Learning
Add import * as d3 from 'd3’; to the files:
dataset.ts
heatmap.ts
linechart.ts
playground.ts
Launch the app: ng serve
55. 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
56. About Me
I provide training for the following:
=> Deep Learning/TensorFlow/Keras
=> Android
=> Angular 4
57. Recent/Upcoming 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)