deeplearning—book—整理——intro

//2016/12/28

1、人工智能真正的难题是是什么？

--The true challenge to artificial intelligence proved to be solvingthe tasks that are easy for people to perform but hard for people to describeformally—problems that we solve intuitively, that feel automatic, like recognizingspoken words or faces in images.

2、deep learning的一种解释：

--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 a hierarchy of concepts, witheach 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 conceptsby 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. For this reason, we call this approach toAI deep learning.

3、machine learning的一种解释：

--The difficulties faced by systems relying on hard-coded knowledge suggest that AI systems need the ability to acquire their own knowledge, by extracting patterns from raw data. This capability is known asmachine learning.

4、representation learning的一种解释：

--One solution to this problem is to use machine learning to discover not onlythe mapping from representation to output but also the representation itself.This approach is known asrepresentation learning.

5、representation learning的精髓案例：

The quintessential example of a representation learning algorithm isthe au-toencoder.

6、deeplearning解决了什么？

--When it is nearly as difficult to obtain a representation as to solve theoriginal problem, representation learning does not, at first glance, seem to help us.

--Deep learningsolves this central problem in representation learning by introducing representations that are expressed in terms of other, simpler representations.

7、feedforward deepnetwork、MLP与deeplearning：

--The quintessential example of a deep learning model is thefeedforward deepnetwork ormultilayer perceptron(MLP).

8、弄清deeplearning与machine learning以及AI的关系：

--A Venn diagram showing how deep learning is a kind of representation learning,which is in turn a kind of machine learning, which is used for many but not all approachesto AI. Each section of the Venn diagram includes an example of an AI technology.

--Flowcharts showing how the different parts of an AI system relate to eachother within different AI disciplines. Shaded boxes indicate components that are able tolearn from data.