斯坦福公开课深度学习Deep Learning

Deep Learning

Samy Bengio, Tom Dean and Andrew Ng

COURSE DESCRIPTION

In this course, you'll learn about some of the most widely used and successful machine learning techniques. You'll have the opportunity to implement these algorithms yourself, and gain practice with them. These algorithms will also form the basic building blocks
of deep learning algorithms.

I. MATLAB AND LINEAR ALGEBRA TUTORIAL

Matlab
tutorial (external link)


Linear
algebra review: What are matrices/vectors, and how to add/substract/multiply them. (pdf)

II. LINEAR REGRESSION I

Supervised
Learning Introduction(1.2x)(1.5x)


Model
Representation(1.2x)(1.5x)


Cost
Function(1.2x)(1.5x)


Gradient
Descent(1.2x)(1.5x)


Gradient
Descent for Linear Regression(1.2x)(1.5x)


Vectorized
Implementation(1.2x)(1.5x)


Exercise:
Linear Regression

III. LINEAR REGRESSION II

Feature
Scaling(1.2x)(1.5x)


Learning
Rate(1.2x)(1.5x)


Features
and Polynomial Regression(1.2x)(1.5x)


Normal
Equations(1.2x)(1.5x)


Exercise:
Multivariance Linear Regression

IV. LOGISTIC REGRESSION

Classification(1.2x)(1.5x)


Model(1.2x)(1.5x)


Optimization
Objective I(1.2x)(1.5x)


Optimization
Objective II(1.2x)(1.5x)


Gradient
Descent(1.2x)(1.5x)


Newton's
Method I(1.2x)(1.5x)


Newton's
Method II(1.2x)(1.5x)


Gradient
Descent vs Newton's Method(1.2x)(1.5x)


Exercise:
Logistic Regression

V. REGULARIZATION (OPTIONAL)

The
Problem Of Overfitting(1.2x)(1.5x)


Optimization
Objective(1.2x)(1.5x)


Common
Variations(1.2x)(1.5x)


Regularized
Linear Regression(1.2x)(1.5x)


Regularized
Logistic Regression(1.2x)(1.5x)


Exercise:
Regularization

from: http://openclassroom.stanford.edu/MainFolder/CoursePage.php?course=DeepLearning