Advanced Spark and TensorFlow Meetup 08-04-2016 Fundamental Algorithms of Neural Networks including Gradient Descent, Back Propagation, Auto Differentiation, Partial Derivatives, Chain Rule

1. Backprop,
Gradient Descent,
And Auto Differentiation
Sam Abrahams, Memdump LLC

2. https://goo.gl/tKOvr
7
Link to these slides:

3. YO!
I am Sam Abrahams
I am a data scientist and engineer.
You can find me on GitHub @samjabrahams
Buy my book:
TensorFlow for Machine Intelligence

4. 1.
Gradient
Descent
Guess and Check
for Adults

5. Gradient Descent Outline
▣ Problem: fit data
▣ Basic OLS linear regression
▣ Visualize error curve and regression line
▣ Step by step through changes

6. Scatter Plot
Simple Start: Linear Regression

7. Ordinary Least Squares Linear Regression
Simple Start: Linear Regression

8. Simple Start: Linear Regression
▣ Want to find a model that can fit our data
▣ Could do it algebraically…
▣ BUT that doesn’t generalize well

9. Simple Start: Linear Regression
▣ Step back: what does ordinary linear regression
try to do?
▣ Minimize the sum of (or average) squared error
▣ How else could we minimize?

10. Gradient Descent
▣ Start with a random guess
▣ Use the derivative (gradient when dealing with
multiple variables) to get the slope of the error
curve
▣ Move our parameters to move down the error
curve

11. Single Variable Cost Curve
J (cost)
W

12. Single Variable Cost Curve
J (cost)
Random guess put us here
W

13. ∂
W
J (cost)
∂J
∂W

14. ∂
W
J (cost)
∂J
∂W < 0

15. ∂
W
J (cost)
∂J
∂W < 0; move to the right!

16. Single Variable Cost Curve
J (cost)
W

17. Single Variable Cost Curve
J (cost)
W
∂J
∂W

18. Single Variable Cost Curve
J (cost)
W
∂J
∂W < 0

19. Single Variable Cost Curve
J (cost)
W
∂J
∂W < 0; move to the right!

20. Single Variable Cost Curve
J (cost)
W

21. Single Variable Cost Curve
J (cost)
W
∂J
∂W

22. Single Variable Cost Curve
J (cost)
W
∂J
∂W

23. Single Variable Cost Curve
J (cost)
∂J
∂W
W

24. 1.5
Gradient
Descent Variants
Intelligent descent
into madness

25. Gradient Descent Variants
▣ There are additional techniques that can help
speed up (or otherwise improve) gradient
descent
▣ The next slides describe some of these!
▣ More details (and some awesome visuals)
here: article by Sebastian Ruder

26. Gradient Descent
▣Get true gradient with respect to all examples
▣One step = one epoch
▣Slow and generally unfeasible for large training
sets

27. Gradient Descent

28. Stochastic Gradient Descent
▣Basic idea: approximate derivative by only using
one example
▣“Online learning”
▣Update weights after each example

29. Stochastic Gradient Descent

30. Mini-Batch Gradient Descent
▣Similar idea to stochastic gradient descent
▣Approximate derivative with a sample batch of
examples
▣Middle ground between “true” stochastic
gradient and full gradient descent

31. Mini-Batch Gradient Descent

32. Momentum
▣Idea: if we see multiple gradients in a row with
same direction, we should increase our learning
rate
▣Accumulate a “momentum” vector to speed up
descent

33. Without Momentum

34. Momentum

35. Nesterov Momentum
▣ Idea: before updating our weights, look ahead
to where we have accumulated momentum
▣ Adjust our update based on “future”

36. Nesterov Momentum
Source: Lecture by Geoffrey Hinton
Momentum Vector
Gradient/correction
Nesterov steps
Standard momentum steps

37. AdaGrad
▣ Idea: update individual weights differently
depending on how frequently they change
▣ Keeps a running tally of previous updates for
each weight, and divides new updates by a
factor of the previous updates
▣ Downside: for long running training,
eventually all gradients diminish
▣ Paper on jmlr.org

38. AdaDelta / RMSProp
▣ Two slightly different algorithms with same
concept: only keep a window of the previous
n gradients when scaling updates
▣ Seeks to reduce diminishing gradient problem
with AdaGrad
▣ AdaDelta Paper on arxiv.org

39. Adam
▣ Adam expands on the concepts introduced
with AdaDelta and RMSProp
▣ Uses both first order and second order
moments, decayed over time
▣ Paper on arxiv.org

40. 2.
Forward & Back
Propagation
The Chain Rule
got the last laugh,
high-school-you

41. Beyond OLS Regression
▣ Can’t do everything with linear regression!
▣ Nor polynomial…
▣ Why can’t we let the computer figure out how
to model?

42. Neural Networks: Idea
▣ Chain together non-linear functions
▣ Have lots of parameters that can be adjusted
▣ These “weights” determine the model function

43. Feed forward neural network
+1 +1
x1
x2
+1
l (2)
l (3)
l (4)
l (1)
input hidden 1 hidden 2 output
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ

44. σ
σ
σ
+1
σ
σ
σ
+1
SM
SM
SM
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
W(l)
: weight matrix for layer l
z(l)
: input into layer l
σ: sigmoid (logistic) function
SM: Softmax function

45. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Layer 1
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

46. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Layer 2
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

47. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Layer 3
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

48. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Layer 4
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

49. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Biases (constant units)
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

50. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Input
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

51. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Weight matrices
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

52. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Layer inputs, z(l)
W(l)
: weight matrix for layer l
z(l)
: input into layer l
z(l)
= W(l-1)
a(l-1)
+ b(l-1)
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

53. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Activation vectors
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

54. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Sigmoid activation function
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
σ: sigmoid (logistic) function
SM: Softmax function

55. SM
SM
SM
σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
Softmax activation function
W(l)
: weight matrix for layer l
z(l)
: input into layer l
σ: sigmoid (logistic) function
SM: Softmax function

56. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
σ: sigmoid (logistic) function
SM: Softmax function
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
W(l)
: weight matrix for layer l
z(l)
: input into layer l
Output
SM
SM
SM

57. x1
x2
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
Forward Propagation
Input vector is passed into the network

58. x1
x2
+1
W(1)
a(2)
W(2)
W(3)
a(3)
a(4)
Forward Propagation
Input is multiplied with W(1)
weight matrix and added with
layer 1 biases to calculate z(2)
z(2)
= W(1)
x + b(1)

59. σ
σ
σ
x1
x2
+1
W(1)
a(2)
Forward Propagation
W(2)
W(3)
a(3)
a(4)
Activation value for the second layer is calculated by passing
z(2)
into some function. In this case, the sigmoid function.
a(2)
= σ(z(2)
)

60. σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
a(2)
Forward Propagation
W(3)
a(3)
a(4)
z(3)
is calculated by multiplying a(2)
vector with W(2)
weight
matrix and adding layer 2 biases
z(3)
= W(2)
a(2)
+ b(2)

61. σ
σ
σ
+1
σ
σ
σ
x1
x2
+1
W(1)
W(2)
a(2)
a(3)
Forward Propagation
Similar to previous layer, a(3)
is calculated by passing z(3)
into
the sigmoid function
a(3)
= σ(z(3)
)
W(3)

62. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
Forward Propagation
z(4)
is calculated by multiplying a(3)
vector with W(3)
weight
matrix and adding layer 3 biases
z(4)
= W(3)
a(3)
+ b(3)
a(4)

63. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
SM
SM
SM
Forward Propagation
For the final layer, we calculate a(4)
by passing z(4)
into the
Softmax function
a(4)
= SM(z(4)
)

64. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
SM
SM
SM
Forward Propagation
We then make our prediction based on the final layer’s output

65. Page of Math
z(2)
= W(1)
x + b(1)
z(3)
= W(2)
a(2)
+ b(2)
z(4)
= W(3)
a(3)
+ b(3)
a(2)
= σ(z(2)
)
a(3)
= σ(z(3)
)
a(4)
= ŷ = SM(z(4)
)

66. Goal:
Find which direction to shift weights
How:
Find partial derivatives of the cost with
respect to weight matrices
How (again):
Chain rule the sh*t out of this mofo

67. DANGER:
MATH

68. Chain Rule Reminder

69. Chain Rule Reminder

70. Chain rule example
Find derivative with respect to x:

71. Chain rule example
First split into two functions:

72. Chain rule example
Then get derivative of components:

73. Chain rule example

74. Chain rule example

75. Chain rule example

76. Chain rule example

77. Chain rule example

78. Chain rule example

79. Chain rule example

80. DEEPER

81. DEEPER
Want:

82. DEEPER

83. DEEPER
NOTE: “Cancelling out” isn’t how the math actually works. But it’s a handy way to think about it.

84. DEEPER
NOTE: “Cancelling out” isn’t how the math actually works. But it’s a handy way to think about it.

85. DEEPER
NOTE: “Cancelling out” isn’t how the math actually works. But it’s a handy way to think about it.

86. Back Prop
Back to backpropagation:
Want:

87. Return of Page of Math
z(2)
= W(1)
x + b(1)
z(3)
= W(2)
a(2)
+ b(2)
z(4)
= W(3)
a(3)
+ b(3)
a(2)
= σ(z(2)
)
a(3)
= σ(z(3)
)
a(4)
= ŷ = SM(z(4)
)

88. Partials, step by step
a(4)
= ŷ = SM(z(4)
)
With cross entropy loss:

89. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
c
o
s
t
σ: sigmoid (logistic) function
SM: Softmax function
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
Back Propagation
Want:

90. Partials, step by step

91. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
c
o
s
t
σ: sigmoid (logistic) function
SM: Softmax function
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
Back Propagation
Want:

92. Partials, step by step

93. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
c
o
s
t
σ: sigmoid (logistic) function
SM: Softmax function
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
Back Propagation
Want:

94. Partials, step by step

95. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
c
o
s
t
σ: sigmoid (logistic) function
SM: Softmax function
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
Back Propagation
Want:

96. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
c
o
s
t
σ: sigmoid (logistic) function
SM: Softmax function
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
Back Propagation
Want:

97. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
c
o
s
t
σ: sigmoid (logistic) function
SM: Softmax function
xi
: input value
ŷ: output vector
+1: bias (constant) unit
a(l)
: activation vector for layer l
W(l)
: weight matrix for layer l
z(l)
: input into layer l
SM
SM
SM
Back Propagation
Want:

98. Partials, step by step

99. As programmers...
How do we NOT
do this ourselves?
We’re lazy by trade.

100. 3.
Automatic
Differentiation
Bringing sexy lazy
back

101. Why not hard code?
▣ Want to iterate fast!
▣ Want flexibility
▣ Want to reuse our code!

102. Auto-Differentiation: Idea
▣ Use functions that have easy-to-compute
derivatives
▣ Compose these functions to create more
complex super-model
▣ Use the chain rule to get partial derivatives of
the model

103. What makes a “good” function?
▣ Obvious stuff: differentiable (continuously
and smoothly!)
▣ Simple operations: add, subtract, multiply
▣ Reuse previous computation

104. Nice functions: sigmoid

105. Nice functions: sigmoid

106. Nice functions: hyperbolic tangent

107. Nice functions: hyperbolic tangent

108. Nice functions: Rectified linear unit

109. Nice functions: Rectified linear unit

110. Nice functions: Addition

111. Nice functions: Addition

112. Nice functions: Multiplication

113. Good news:
Most of these use activation
values! Can store in cache!

114. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
SM
SM
SM
Store activation values for backprop

115. σ
σ
σ
+1
σ
σ
σ
+1
x1
x2
+1
W(1)
W(2)
W(3)
a(2)
a(3)
a(4)
ŷ
SM
SM
SM
Chain rule takes care of the rest

116. It’s Over!
Any questions?
Email: sam@memdump.io
GitHub: samjabrahams
Twitter: @sabraha
Presentation template by SlidesCarnival

118. Neural Network terms
▣ Neuron: a unit that transforms input via an activation function and outputs the result to
other neurons and/or the final result
▣ Activation function: a(l)
, a transformation function, typically non-linear. Sigmoid, ReLU
▣ Bias unit: a trainable scalar shift, typically applied to each non-output layer (think
y-intercept term in the linear function)
▣ Layer: a grouping of “neurons” and biases that (in general) take in values from the same
previous neurons and pass values forwards to the same targets
▣ Hidden layer: A layer that is neither the input layer nor the output layer
▣ Input layer:
▣ Output layer

119. Terminology used
▣ Learning rate
▣ Parameters
▣ Training step
▣ Training example
▣ Epoch vs training time
▣