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