4.66 out of 5
4.66
1645 reviews on Udemy

Modern Deep Learning in Python

Build with modern libraries like Tensorflow, Theano, Keras, PyTorch, CNTK, MXNet. Train faster with GPU on AWS.
Instructor:
Lazy Programmer Inc.
20,475 students enrolled
English [Auto-generated] More
Apply momentum to backpropagation to train neural networks
Apply adaptive learning rate procedures like AdaGrad, RMSprop, and Adam to backpropagation to train neural networks
Understand the basic building blocks of Theano
Build a neural network in Theano
Understand the basic building blocks of TensorFlow
Build a neural network in TensorFlow
Build a neural network that performs well on the MNIST dataset
Understand the difference between full gradient descent, batch gradient descent, and stochastic gradient descent
Understand and implement dropout regularization in Theano and TensorFlow
Understand and implement batch normalization in Theano and Tensorflow
Write a neural network using Keras
Write a neural network using PyTorch
Write a neural network using CNTK
Write a neural network using MXNet

This course continues where my first course, Deep Learning in Python, left off. You already know how to build an artificial neural network in Python, and you have a plug-and-play script that you can use for TensorFlow. Neural networks are one of the staples of machine learning, and they are always a top contender in Kaggle contests. If you want to improve your skills with neural networks and deep learning, this is the course for you.

You already learned about backpropagation, but there were a lot of unanswered questions. How can you modify it to improve training speed? In this course you will learn about batch and stochastic gradient descent, two commonly used techniques that allow you to train on just a small sample of the data at each iteration, greatly speeding up training time.

You will also learn about momentum, which can be helpful for carrying you through local minima and prevent you from having to be too conservative with your learning rate. You will also learn about adaptive learning rate techniques like AdaGradRMSprop, and Adam which can also help speed up your training.

Because you already know about the fundamentals of neural networks, we are going to talk about more modern techniques, like dropout regularization and batch normalization, which we will implement in both TensorFlow and Theano. The course is constantly being updated and more advanced regularization techniques are coming in the near future.

In my last course, I just wanted to give you a little sneak peak at TensorFlow. In this course we are going to start from the basics so you understand exactly what’s going on – what are TensorFlow variables and expressions and how can you use these building blocks to create a neural network? We are also going to look at a library that’s been around much longer and is very popular for deep learning – Theano. With this library we will also examine the basic building blocks – variables, expressions, and functions – so that you can build neural networks in Theano with confidence.

Theano was the predecessor to all modern deep learning libraries today. Today, we have almost TOO MANY options. Keras, PyTorch, CNTK (Microsoft), MXNet (Amazon / Apache), etc. In this course, we cover all of these! Pick and choose the one you love best.

Because one of the main advantages of TensorFlow and Theano is the ability to use the GPU to speed up training, I will show you how to set up a GPU-instance on AWS and compare the speed of CPU vs GPU for training a deep neural network.

With all this extra speed, we are going to look at a real dataset – the famous MNIST dataset (images of handwritten digits) and compare against various benchmarks. This is THE dataset researchers look at first when they want to ask the question, “does this thing work?”

These images are important part of deep learning history and are still used for testing today. Every deep learning expert should know them well.

This course focuses on “how to build and understand“, not just “how to use”. Anyone can learn to use an API in 15 minutes after reading some documentation. It’s not about “remembering facts”, it’s about “seeing for yourself” via experimentation. It will teach you how to visualize what’s happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.

HARD PREREQUISITES / KNOWLEDGE YOU ARE ASSUMED TO HAVE:

  • calculus

  • linear algebra

  • probability

  • Python coding: if/else, loops, lists, dicts, sets

  • Numpy coding: matrix and vector operations, loading a CSV file

  • neural networks and backpropagation

TIPS (for getting through the course):

  • Watch it at 2x.

  • Take handwritten notes. This will drastically increase your ability to retain the information.

  • Write down the equations. If you don’t, I guarantee it will just look like gibberish.

  • Ask lots of questions on the discussion board. The more the better!

  • Realize that most exercises will take you days or weeks to complete.

  • Write code yourself, don’t just sit there and look at my code.

WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

  • Check out the lecture “What order should I take your courses in?” (available in the Appendix of any of my courses, including the free Numpy course)

Introduction and Outline

1
Outline - what did you learn previously, and what will you learn in this course?

In the previous course you learned about softmax and backpropagation. What will you learn in this course?

2
Where does this course fit into your deep learning studies?

Review

1
Review of Basic Concepts
2
Where to get the MNIST dataset and Establishing a Linear Benchmark

Where to get the MNIST dataset, where to put it to run the code from this course correctly. I run through util.py, which contains functions we'll be using throughout the course. I run a logistic regression benchmark to show the accuracy we should aim to beat with deep learning.

Gradient Descent: Full vs Batch vs Stochastic

1
What are full, batch, and stochastic gradient descent?
2
Full vs Batch vs Stochastic Gradient Descent in code

Momentum and adaptive learning rates

1
Using Momentum to Speed Up Training

How can you use momentum to speed up neural network training and get out of local minima?

2
Nesterov Momentum
3
Momentum in Code
4
Variable and adaptive learning rates

Learn about periodic decay of learning rate, exponential decay, 1/t decay, AdaGrad, and RMSprop.

5
Constant learning rate vs. RMSProp in Code
6
Adam Optimization
7
Adam in Code

Choosing Hyperparameters

1
Hyperparameter Optimization: Cross-validation, Grid Search, and Random Search
2
Sampling Logarithmically
3
Grid Search in Code
4
Modifying Grid Search
5
Random Search in Code

Weight Initialization

1
Weight Initialization Section Introduction
2
Vanishing and Exploding Gradients
3
Weight Initialization
4
Local vs. Global Minima
5
Weight Initialization Section Summary

Theano

1
Theano Basics: Variables, Functions, Expressions, Optimization
2
Building a neural network in Theano
3
Is Theano Dead?

TensorFlow

1
TensorFlow Basics: Variables, Functions, Expressions, Optimization
2
Building a neural network in TensorFlow
3
What is a Session? (And more)

GPU Speedup, Homework, and Other Misc Topics

1
Setting up a GPU Instance on Amazon Web Services

I show you how to start a GPU instance on Amazon Web Services (AWS) and prove to you that training a neural network using Theano on the GPU can be much faster than the CPU.

2
Can Big Data be used to Speed Up Backpropagation?
3
Exercises and Concepts Still to be Covered

Here are some things you can do to make yourself more confident with Theano and TensorFlow coding. They are exercises that extend the material taught in this class. I also mention a handful of topics you can look forward to hearing about in future courses.

4
How to Improve your Theano and Tensorflow Skills
5
Theano vs. TensorFlow

Transition to the 2nd Half of the Course

1
Transition to the 2nd Half of the Course

Project: Facial Expression Recognition

1
Facial Expression Recognition Project Introduction
2
Facial Expression Recognition Problem Description
3
The class imbalance problem
4
Utilities walkthrough
5
Class-Based ANN in Theano
6
Class-Based ANN in TensorFlow
7
Facial Expression Recognition Project Summary

Modern Regularization Techniques

1
Modern Regularization Techniques Section Introduction
2
Dropout Regularization
3
Dropout Intuition
4
Noise Injection
5
Modern Regularization Techniques Section Summary

Batch Normalization

1
Batch Normalization Introduction
2
Exponentially-Smoothed Averages
3
Batch Normalization Theory
4
Batch Normalization Tensorflow (part 1)
5
Batch Normalization Tensorflow (part 2)
6
Batch Normalization Theano (part 1)
7
Batch Normalization Theano (part 2)
8
Noise Perspective
9
Batch Normalization Summary

Keras

1
Keras Discussion
2
Keras in Code
3
Keras Functional API

PyTorch

1
PyTorch Basics
2
PyTorch Dropout
3
PyTorch Batch Norm

PyTorch, CNTK, and MXNet

1
PyTorch, CNTK, and MXNet

Appendix

1
What is the Appendix?
2
What's the difference between "neural networks" and "deep learning"?
3
Manually Choosing Learning Rate and Regularization Penalty
4
Windows-Focused Environment Setup 2018
5
How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
6
How to Succeed in this Course (Long Version)
7
How to Code by Yourself (part 1)
8
How to Code by Yourself (part 2)
9
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
10
Proof that using Jupyter Notebook is the same as not using it
11
How to Uncompress a .tar.gz file
12
Python 2 vs Python 3
13
What order should I take your courses in? (part 1)
14
What order should I take your courses in? (part 2)
You can view and review the lecture materials indefinitely, like an on-demand channel.
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!
4.7
4.7 out of 5
1645 Ratings

Detailed Rating

Stars 5
1117
Stars 4
402
Stars 3
78
Stars 2
28
Stars 1
20
e1492a221e9d29fe568f6d3353653ae1
30-Day Money-Back Guarantee

Includes

9 hours on-demand video
Full lifetime access
Access on mobile and TV
Certificate of Completion