Deep Learning and Neural Networks in Python
This course will get you started in building your FIRST artificial neural network using deep learning techniques. Following my previous course on logistic regression, we take this basic building block, and build fullon nonlinear neural networks right out of the gate using Python and Numpy. All the materials for this course are FREE.
“If you can’t implement it, you don’t understand it”
 Or as the great physicist Richard Feynman said: “What I cannot create, I do not understand”.
 My courses are the ONLY courses where you will learn how to implement machine learning algorithms from scratch
 Other courses will teach you how to plug in your data into a library, but do you really need help with 3 lines of code?
 After doing the same thing with 10 datasets, you realize you didn’t learn 10 things. You learned 1 thing, and just repeated the same 3 lines of code 10 times…
Deep Learning and Neural Networks in Python:
 calculus (taking derivatives)
 matrix arithmetic
 probability
 Python coding: if/else, loops, lists, dicts, sets
 Numpy coding: matrix and vector operations, loading a CSV file
 Be familiar with basic linear models such as linear regression and logistic regression
WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:
 Check out the lecture “Machine Learning and AI Prerequisite Roadmap” (available in the FAQ of any of my courses, including the free Numpy course)
Review
Preliminaries: From Neurons to Neural Networks
Classifying more than 2 things at a time
Training a neural network

12Prediction: Section Introduction and Outline

13From Logistic Regression to Neural Networks

14Interpreting the Weights of a Neural Network

15Softmax
What's the function we use to classify more than 2 things?

16Sigmoid vs. Softmax

17Feedforward in SlowMo (part 1)

18Feedforward in SlowMo (part 2)

19Where to get the code for this course

20Softmax in Code
How do we code the softmax in Python?

21Building an entire feedforward neural network in Python
Let's extend softmax and code the entire calculation from input to output.

22ECommerce Course Project: PreProcessing the Data

23ECommerce Course Project: Making Predictions

24Prediction Quizzes

25Prediction: Section Summary

26Suggestion Box
Practical Machine Learning

27Training: Section Introduction and Outline

28What do all these symbols and letters mean?

29What does it mean to "train" a neural network?

30How to Brace Yourself to Learn Backpropagation

31Categorical CrossEntropy Loss Function

32Training Logistic Regression with Softmax (part 1)

33Training Logistic Regression with Softmax (part 2)

34Backpropagation (part 1)

35Backpropagation (part 2)

36Backpropagation in code
How to code bacpropagation in Python using numpy operations vs. slow for loops.

37Backpropagation (part 3)

38The WRONG Way to Learn Backpropagation

39ECommerce Course Project: Training Logistic Regression with Softmax

40ECommerce Course Project: Training a Neural Network

41Training Quiz

42Training: Section Summary
TensorFlow, exercises, practice, and what to learn next

43Practical Issues: Section Introduction and Outline

44Donut and XOR Review
What are the donut and XOR problems again?

45Donut and XOR Revisited
We look again at the XOR and donut problem from logistic regression. The features are now learned automatically.

46Neural Networks for Regression

47Common nonlinearities and their derivatives
sigmoid, tanh, relu along with their derivatives

48Practical Considerations for Choosing Activation Functions

49Hyperparameters and CrossValidation
Tips on choosing learning rate, regularization penalty, number of hidden units, and number of hidden layers.

50Manually Choosing Learning Rate and Regularization Penalty

51Why Divide by Square Root of D?

52Practical Issues: Section Summary
Project: Facial Expression Recognition

53TensorFlow plugandplay example
A look at Google's new TensorFlow library.

54Visualizing what a neural network has learned using TensorFlow Playground

55Where to go from hereWhat did you learn? What didn't you learn? Where can you learn more?

56You know more than you think you know

57How to get good at deep learning + exercises

58Deep neural networks in just 3 lines of code with SciKit Learn
Backpropagation Supplementary Lectures

59Facial Expression Recognition Project Introduction

60Facial Expression Recognition Problem Description

61The class imbalance problem

62Utilities walkthrough

63Facial Expression Recognition in Code (Binary / Sigmoid)

64Facial Expression Recognition in Code (Logistic Regression Softmax)

65Facial Expression Recognition in Code (ANN Softmax)

66Facial Expression Recognition Project Summary