Deep Learning

The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular.

**Tag(s):**
Machine Learning

**Publication date**: 18 Nov 2016

**ISBN-10**:
0262035618

**ISBN-13**:
9780262035613

**Paperback**:
800 pages

**Views**: 8,691

Deep Learning

The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular.

From the Introduction:

In the early days of artiﬁcial intelligence, the ﬁeld rapidly tackled and solved problems that are intellectually diffcult for human beings but relatively straight-forward for computers—problems that can be described by a list of formal, mathematical rules. The true challenge to artiﬁcial intelligence proved to be solving the tasks that are easy for people to perform but hard for people to describe formally—problems that we solve intuitively, that feel automatic, like recognizing spoken words or faces in images.

This book is about a solution to these more intuitive problems. This solution isto allow computers to learn from experience and understand the world in terms of ahierarchy of concepts, with each concept deﬁned in terms of its relation to simpler concepts. By gathering knowledge from experience, this approach avoids the need for human operators to formally specify all of the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones. If we draw a graph showing how these concepts are built on top of each other, the graph is deep, with many layers. Forthis reason, we call this approach to AI deep learning.

In the early days of artiﬁcial intelligence, the ﬁeld rapidly tackled and solved problems that are intellectually diffcult for human beings but relatively straight-forward for computers—problems that can be described by a list of formal, mathematical rules. The true challenge to artiﬁcial intelligence proved to be solving the tasks that are easy for people to perform but hard for people to describe formally—problems that we solve intuitively, that feel automatic, like recognizing spoken words or faces in images.

This book is about a solution to these more intuitive problems. This solution isto allow computers to learn from experience and understand the world in terms of ahierarchy of concepts, with each concept deﬁned in terms of its relation to simpler concepts. By gathering knowledge from experience, this approach avoids the need for human operators to formally specify all of the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones. If we draw a graph showing how these concepts are built on top of each other, the graph is deep, with many layers. Forthis reason, we call this approach to AI deep learning.

Tweet

About The Author(s)

Yoshua Bengio is Full Professor of the Department of Computer Science and Operations Research, head of the Machine Learning Laboratory (MILA), CIFAR Program co-director of the CIFAR Neural Computation and Adaptive Perception program, Canada Research Chair in Statistical Learning Algorithms, and he also holds the NSERC-Ubisoft industrial chair. His main research ambition is to understand principles of learning that yield intelligence.

Book Categories

Computer Science
Introduction to Computer Science
Introduction to Computer Programming
Algorithms and Data Structures
Artificial Intelligence
Computer Vision
Machine Learning
Neural Networks
Game Development and Multimedia
Data Communication and Networks
Coding Theory
Computer Security
Information Security
Cryptography
Information Theory
Computer Organization and Architecture
Operating Systems
Image Processing
Parallel Computing
Concurrent Programming
Relational Database
Document-oriented Database
Data Mining
Big Data
Data Science
Digital Libraries
Compiler Design and Construction
Functional Programming
Logic Programming
Object Oriented Programming
Formal Methods
Software Engineering
Agile Software Development
Information Systems
Geographic Information System (GIS)

Mathematics
Mathematics
Algebra
Abstract Algebra
Linear Algebra
Number Theory
Numerical Methods
Precalculus
Calculus
Differential Equations
Category Theory
Proofs
Discrete Mathematics
Theory of Computation
Graph Theory
Real Analysis
Complex Analysis
Probability
Statistics
Game Theory
Queueing Theory
Operations Research
Computer Aided Mathematics

Supporting Fields
Web Design and Development
Mobile App Design and Development
System Administration
Cloud Computing
Electric Circuits
Embedded System
Signal Processing
Integration and Automation
Network Science
Project Management

Operating System
Programming/Scripting
Ada
Assembly
C / C++
Common Lisp
Forth
Java
JavaScript
Lua
Microsoft .NET
Rexx
Perl
PHP
Python
R
Rebol
Ruby
Scheme
Tcl/Tk

Miscellaneous
Sponsors