|Book Name:||Deep Learning|
In the dawn of artificial intelligence, the field quickly tackled and solved problems that were intellectually difficult for humans but relatively easy for computers, problems that can be described by a list of formal mathematical rules. The real challenge for AI has turned out to be solving tasks that are easy for people to perform but difficult to formally describe, problems that we solve intuitively, that seem automatic, such as recognizing spoken words or faces in images.
This book deals with a solution to these more intuitive problems. This solution allows computers to learn from experience and understand the world in terms of a hierarchy of concepts, with each concept defined by its relationship to simpler concepts. By gathering knowledge from experience, this approach avoids the need for human operators to formally specify all necessary computer knowledge. The concept hierarchy allows the computer to learn complicated concepts by building them from simpler ones. If we draw a graph that shows how these concepts build on top of each other, the graph is deep, with many levels. For this reason, we call this AI approach deep learning.
Author(s): Ian Goodfellow, Yoshua Bengio, Aaron Courville
Publisher: MIT, Year: 2017
MIT Deep Learning Book in PDF format (by Ian Goodfellow, Yoshua Bengio and Aaron Courville).
Related More Books
Search Results For Keywords Deep Learning
deep learning ian goodfellow github
deep learning ian goodfellow ppt
deep learning ian goodfellow citation
deep learning ian goodfellow goodreads