STARTS

Nov 28th 2016

Neural Networks for Machine Learning (Coursera)

Created by:Delivered by:
Taught by:

Learn about artificial neural networks and how they're being used for machine learning, as applied to speech and object recognition, image segmentation, modeling language and human motion, etc. We'll emphasize both the basic algorithms and the practical tricks needed to get them to work well.

This course contains the same content presented on Coursera beginning in 2013. It is not a continuation or update of the original course. It has been adapted for the new platform.

Please be advised that the course is suited for an intermediate level learner - comfortable with calculus and with experience programming (Python).


Syllabus


WEEK 1

Introduction

Introduction to the course - machine learning and neural nets

Graded: Lecture 1 Quiz


WEEK 2

The Perceptron learning procedure

An overview of the main types of neural network architecture

Graded: Lecture 2 Quiz


WEEK 3

The backpropagation learning proccedure

Learning the weights of a linear neuron

Graded: Lecture 3 Quiz

Graded: Programming Assignment 1: The perceptron learning algorithm.


WEEK 4

Learning feature vectors for words

Learning to predict the next word

Graded: Lecture 4 Quiz


WEEK 5

Object recognition with neural nets

In this module we look at why object recognition is difficult.

Graded: Lecture 5 Quiz

Graded: Programming Assignment 2: Learning Word Representations.


WEEK 6

Optimization: How to make the learning go faster

We delve into mini-batch gradient descent as well as discuss adaptive learning rates.

Graded: Lecture 6 Quiz


WEEK 7

Recurrent neural networks

This module explores training recurrent neural networks

Graded: Lecture 7 Quiz


WEEK 8

More recurrent neural networks

We continue our look at recurrent neural networks

Graded: Lecture 8 Quiz


WEEK 9

Ways to make neural networks generalize better

We discuss strategies to make neural networks generalize better

Graded: Lecture 9 Quiz

Graded: Programming assignment 3: Optimization and generalization


WEEK 10

Combining multiple neural networks to improve generalization

This module we look at why it helps to combine multiple neural networks to improve generalization

Graded: Lecture 10 Quiz


WEEK 11

Hopfield nets and Boltzmann machines

Graded: Lecture 11 Quiz


WEEK 12

Restricted Boltzmann machines (RBMs)

This module deals with Boltzmann machine learning

Graded: Lecture 12 Quiz


WEEK 13

Stacking RBMs to make Deep Belief Nets

Graded: Programming Assignment 4: Restricted Boltzmann Machines

Graded: Lecture 13 Quiz


WEEK 14

Deep neural nets with generative pre-training

Graded: Lecture 14 Quiz


WEEK 15

Modeling hierarchical structure with neural nets

Graded: Lecture 15 Quiz

Graded: Final Exam


WEEK 16

Recent applications of deep neural nets