Introduction - Deep Learning

Introduction

Lecture slides for Chapter 1 of Deep Learning



Ian Goodfellow

2016-09-26

Representations Matter

APTER 1. INTRODUCTION

Polar coordinates

¦È

y

Cartesian coordinates

x

r

ure 1.1: Example of di?erent representations:

Figure 1.1 suppose we want to separate

(Goodfellow 2016)

Depth: Repeated Composition

CHAPTER 1. INTRODUCTION

CAR

PERSON

ANIMAL

Output

(object identity)

3rd hidden layer

(object parts)

2nd hidden layer

(corners and

contours)

1st hidden layer

(edges)

Visible layer

(input pixels)

Figure 1.2: Illustration of a deep learning model. It is di?cult for a computer to understand

the meaning of raw sensory input data, such as this image represented as a collection

Figure 1.2

(Goodfellow 2016)

Computational Graphs

CHAPTER 1. INTRODUCTION

Element

Set

+

?

Element

Set

+

?

w1

?

x1

w2

Logistic

Regression

x2

Logistic

Regression

w

x

Figure 1.3: Illustration of computational graphs mapping an input to an output where

Figure

each node performs an operation. Depth

is the1.3

length of the longest path from(Goodfellow

input

2016)to

Machine Learning and AI

Deep learning

Example:

MLPs

Example:

Shallow

autoencoders

Example:

Logistic

regression

Example:

Knowledge

bases

Representation learning

Machine learning

AI

Figure 1.4

Figure 1.4: A Venn diagram showing how deep learning is a kind of representation learning,

(Goodfellow 2016)

 ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download