Data Science: Deep Learning and Neural Networks in Python
The MOST in-depth look at neural network theory for machine learning, with both pure Python and Tensorflow code
- Description
- Curriculum
- FAQ
- Reviews
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 full-on non-linear 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
WHATÂ ORDERÂ SHOULDÂ IÂ TAKEÂ YOURÂ COURSESÂ IN?:
- Check out the lecture “Machine Learning and AIÂ 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
-
12
Prediction: Section Introduction and Outline -
13
From Logistic Regression to Neural Networks
-
14
Interpreting the Weights of a Neural Network
-
15
Softmax
What's the function we use to classify more than 2 things?
-
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
How do we code the softmax in Python?
-
21
Building an entire feedforward neural network in Python
Let's extend softmax and code the entire calculation from input to output.
-
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
Practical Machine Learning
-
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
How to code bacpropagation in Python using numpy operations vs. slow for loops.
-
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
TensorFlow, exercises, practice, and what to learn next
-
43
Practical Issues: Section Introduction and Outline
-
44
Donut and XOR Review
What are the donut and XOR problems again?
-
45
Donut and XOR Revisited
We look again at the XOR and donut problem from logistic regression. The features are now learned automatically.
-
46
Neural Networks for Regression
-
47
Common nonlinearities and their derivatives
sigmoid, tanh, relu along with their derivatives
-
48
Practical Considerations for Choosing Activation Functions
-
49
Hyperparameters and Cross-Validation
Tips on choosing learning rate, regularization penalty, number of hidden units, and number of hidden layers.
-
50
Manually Choosing Learning Rate and Regularization Penalty
-
51
Why Divide by Square Root of D?
-
52
Practical Issues: Section Summary
Project: Facial Expression Recognition
-
53
TensorFlow plug-and-play example
A look at Google's new TensorFlow library.
-
54
Visualizing what a neural network has learned using TensorFlow Playground
-
55
Where to go from hereWhat did you learn? What didn't you learn? Where can you learn more?
-
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
Backpropagation Supplementary Lectures
-
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
Higher-Level Discussion
Setting Up Your Environment (FAQ by Student Request)
Extra Help With Python Coding for Beginners (FAQ by Student Request)
Effective Learning Strategies for Machine Learning (FAQ by Student Request)
How long do I have access to the course materials?
You can view and review the lecture materials indefinitely, like an on-demand channel.
Can I take my courses with me wherever I go?
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
Stars 5
5889
Stars 4
3046
Stars 3
476
Stars 2
107
Stars 1
101
