English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 4 Hours | Lec: 33 | 500 MB
Take deep learning to the next level with SGD, Nesterov momentum, RMSprop, Theano, TensorFlow, and using the GPU on AWS.
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 (and because of that, this course contains basically NO MATH), 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 AdaGrad and RMSprop 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, 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.
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 known benchmarks.
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.
Outline the MNIST dataset and Linear Logistic Regression Benchmark
1 Outline - what did you learn previously and what will you learn in this course
2 Where does this course fit into your deep learning studies
3 How to Succeed in this Course
4 Where to get the MNIST dataset and Establishing a Linear Benchmark
Gradient Descent Full vs Batch vs Stochastic
5 What are full batch and stochastic gradient descent
6 Full vs Batch vs Stochastic Gradient Descent in code
Momentum and adaptive learning rates
8 Code for training a neural network using momentum
9 Variable and adaptive learning rates
10 Constant learning rate vs. RMSProp in Code
11 Hyperparameter Optimization Cross-validation Grid Search and Random Search
12 Grid Search in Code
13 Random Search in Code
14 Theano Basics Variables Functions Expressions Optimization
15 Building a neural network in Theano
16 TensorFlow Basics Variables Functions Expressions Optimization
17 Building a neural network in TensorFlow
GPU Speedup Homework and Other Misc Topics
18 Setting up a GPU Instance on Amazon Web Services
19 Can Big Data be used to Speed Up Backpropagation
20 Exercises and Concepts Still to be Covered
21 How to Improve your Theano and Tensorflow Skills
22 Theano vs. TensorFlow
Modern Regularization Techniques
23 Dropout Regularization
24 Dropout Intuition
Project Facial Expression Recognition
25 Facial Expression Recognition Problem Description
26 The class imbalance problem
27 Utilities walkthrough
28 Class-Based ANN in Theano
29 Class-Based ANN in TensorFlow
30 Manually Choosing Learning Rate and Regularization Penalty
31 How to install Numpy Scipy Matplotlib Pandas IPython Theano and TensorFlow
32 How to Code by Yourself part 1
33 How to Code by Yourself part 2