Deep learning creates representations that are expressed in terms of other, simpler representations
Mo Data stashed this in Machine Learning
Deep Learning for AI
Inventors have long dreamed of creating machines that think. Ancient Greek myths tell of intelligent objects, such as animated statues of human beings and tables that arrive full of food and drink when called . When programmable computers were ﬁrst conceived,people wondered whether they might become intelligent, over a hundred years before one was built (Lovelace, 1842). Today, artiﬁcial intelligence (AI) is a thriving ﬁeld with many practical applications and active research topics. We look to intelligent software to automate routine labor, make predictions in ﬁnance and diagnoses in medicine, and to support basic scientiﬁc research. This book is about deep learning, an approach toAI based on enabling computers to learn from experience and understand the world in terms of a hierarchy of concepts, with each concept deﬁned in terms of of its relation to simpler concepts.
Deep learning solves this central problem in representation learning by introducing representations that are expressed in terms of other, simpler representations. Deep learning allows the computer to build complex concepts out of simpler concepts. Fig. 1.1shows how a deep learning system can represent the concept of an image of a person by combining simpler concepts, such as corners and contours, which are in turn deﬁned in terms of edges.