Data Science: Deep Learning and Neural Networks in Python

Data Science: Deep Learning and Neural Networks in Python

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 11h 09m | 1.58 GB

The MOST in-depth look at neural network theory, and how to code one with pure Python and Tensorflow

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 full-on non-linear neural networks right out of the gate using Python and Numpy. All the materials for this course are FREE.

We extend the previous binary classification model to multiple classes using the softmax function, and we derive the very important training method called “backpropagation” using first principles. I show you how to code backpropagation in Numpy, first “the slow way”, and then “the fast way” using Numpy features.

Next, we implement a neural network using Google’s new TensorFlow library.

You should take this course if you are interested in starting your journey toward becoming a master at deep learning, or if you are interested in machine learning and data science in general. We go beyond basic models like logistic regression and linear regression and I show you something that automatically learns features.

This course provides you with many practical examples so that you can really see how deep learning can be used on anything. Throughout the course, we’ll do a course project, which will show you how to predict user actions on a website given user data like whether or not that user is on a mobile device, the number of products they viewed, how long they stayed on your site, whether or not they are a returning visitor, and what time of day they visited.

Another project at the end of the course shows you how you can use deep learning for facial expression recognition. Imagine being able to predict someone’s emotions just based on a picture!

After getting your feet wet with the fundamentals, I provide a brief overview of some of the newest developments in neural networks – slightly modified architectures and what they are used for.

What you’ll learn

  • Learn how Deep Learning REALLY works (not just some diagrams and magical black box code)
  • Learn how a neural network is built from basic building blocks (the neuron)
  • Code a neural network from scratch in Python and numpy
  • Code a neural network using Google’s TensorFlow
  • Describe different types of neural networks and the different types of problems they are used for
  • Derive the backpropagation rule from first principles
  • Create a neural network with an output that has K > 2 classes using softmax
  • Describe the various terms related to neural networks, such as “activation”, “backpropagation” and “feedforward”
  • Install TensorFlow
Table of Contents

1 Introduction and Outline
2 Where to get the code
3 How to Succeed in this Course

4 Review Section Introduction
5 What does machine learning do
6 Neuron Predictions
7 Neuron Training
8 Deep Learning Readiness Test
9 Review Section Summary

Preliminaries From Neurons to Neural Networks
10 Neural Networks with No Math
11 Introduction to the E-Commerce Course Project

Classifying more than 2 things at a time
12 Prediction Section Introduction and Outline
13 From Logistic Regression to Neural Networks
14 Interpreting the Weights of a Neural Network
15 Softmax
16 Sigmoid vs. Softmax
17 Feedforward in Slow-Mo (part 1)
18 Feedforward in Slow-Mo (part 2)
19 Where to get the code for this course
20 Softmax in Code
21 Building an entire feedforward neural network in Python
22 E-Commerce Course Project Pre-Processing the Data
23 E-Commerce Course Project Making Predictions
24 Prediction Quizzes
25 Prediction Section Summary
26 Suggestion Box

Training a neural network
27 Training Section Introduction and Outline
28 What do all these symbols and letters mean
29 What does it mean to train a neural network
30 How to Brace Yourself to Learn Backpropagation
31 Categorical Cross-Entropy Loss Function
32 Training Logistic Regression with Softmax (part 1)
33 Training Logistic Regression with Softmax (part 2)
34 Backpropagation (part 1)
35 Backpropagation (part 2)
36 Backpropagation in code
37 Backpropagation (part 3)
38 The WRONG Way to Learn Backpropagation
39 E-Commerce Course Project Training Logistic Regression with Softmax
40 E-Commerce Course Project Training a Neural Network
41 Training Quiz
42 Training Section Summary

Practical Machine Learning
43 Practical Issues Section Introduction and Outline
44 Donut and XOR Review
45 Donut and XOR Revisited
46 Neural Networks for Regression
47 Common nonlinearities and their derivatives
48 Practical Considerations for Choosing Activation Functions
49 Hyperparameters and Cross-Validation
50 Manually Choosing Learning Rate and Regularization Penalty
51 Why Divide by Square Root of D
52 Practical Issues Section Summary

TensorFlow, exercises, practice, and what to learn next
53 TensorFlow plug-and-play example
54 Visualizing what a neural network has learned using TensorFlow Playground
55 Where to go from here
56 You know more than you think you know
57 How to get good at deep learning + exercises
58 Deep neural networks in just 3 lines of code with Sci-Kit Learn

Project Facial Expression Recognition
59 Facial Expression Recognition Project Introduction
60 Facial Expression Recognition Problem Description
61 The class imbalance problem
62 Utilities walkthrough
63 Facial Expression Recognition in Code (Binary Sigmoid)
64 Facial Expression Recognition in Code (Logistic Regression Softmax)
65 Facial Expression Recognition in Code (ANN Softmax)
66 Facial Expression Recognition Project Summary

Backpropagation Supplementary Lectures
67 Backpropagation Supplementary Lectures Introduction
68 Why Learn the Ins and Outs of Backpropagation
69 Gradient Descent Tutorial
70 Help with Softmax Derivative
71 Backpropagation with Softmax Troubleshooting

Higher-Level Discussion
72 What’s the difference between neural networks and deep learning
73 Who should take this course in 2020 and beyond
74 Who should learn backpropagation in 2020 and beyond
75 Where does this course fit into your deep learning studies

Setting Up Your Environment (FAQ by Student Request)
76 Windows-Focused Environment Setup 2018
77 How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow

Extra Help With Python Coding for Beginners (FAQ by Student Request)
78 How to Uncompress a .tar.gz file
79 How to Code by Yourself (part 1)
80 How to Code by Yourself (part 2)
81 Proof that using Jupyter Notebook is the same as not using it
82 Python 2 vs Python 3

Effective Learning Strategies for Machine Learning (FAQ by Student Request)
83 How to Succeed in this Course (Long Version)
84 Is this for Beginners or Experts Academic or Practical Fast or slow-paced
85 Where does this course fit into your deep learning studies (Old Version)
86 Machine Learning and AI Prerequisite Roadmap (pt 1)
87 Machine Learning and AI Prerequisite Roadmap (pt 2)

Appendix FAQ Finale
88 What is the Appendix
89 BONUS Where to get Udemy coupons and FREE deep learning material