201021_Deep_Learning---1.0、Introduction
一、总结
一句话总结：
Books in Chinese and English can be read together for easy understanding. If you take notes, use English
中英文的书可以一起看，方便理解。做笔记的话，就用英文
1、Ironically, abstract and formal tasks that are among the most difficult mental undertakings for a human being are among the easiest for a computer.？
Computers have long been able to defeat even the best human chess player, but are only recently 【matching some of the abilities of average human beings to recognize objects or speech. 】
A person’s everyday life requires an immense amount of knowledge about the world. 【Much of this knowledge is subjective and intuitive, and therefore difficult to articulate in a formal way.】
Computers need to capture this same knowledge in order to behave in an intelligent way. 【One of the key challenges in artificial intelligence is how to get this informal knowledge into a computer. 】
讽刺的是，抽象和形式化的任务对人类而言是最困难的脑力任务之一，但对计 算机而言却属于最容易的。
计算机早就能够打败人类最好的象棋选手，但直到最近 计算机才在识别对象或语音任务中达到人类平均水平。
一个人的日常生活需要关于 世界的巨量知识。很多这方面的知识是主观的、直观的，因此很难通过形式化的方 式表达清楚。计算机需要获取同样的知识才能表现出智能。人工智能的一个关键挑战就是如何将这些非形式化的知识传达给计算机。
2、This capability is known as machine learning. ？
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 as machine learning.
AI 系统需要具备自己获取知识的能力， 即从原始数据中提取模式的能力。
依靠硬编码的知识体系面对的困难表明，AI 系统需要具备自己获取知识的能力， 即从原始数据中提取模式的能力。这种能力被称为机器学习（machine learning）。
3、It is not surprising that the choice of representation has an enormous effect on the performance of machine learning algorithms. ？
表示的选择会对机器学习算法的性能产生巨大的影响
In the plot on the left,【 we represent some data using Cartesian coordinates, and the task is impossible.】
In the plot on the right,【 we represent the data with polar coordinates and the task becomes simple to solve with a vertical line. 】
Example of different representations: suppose we want to separate two categories of data by drawing a line between them in a scatterplot. In the plot on the left, we represent some data using Cartesian coordinates, and the task is impossible. In the plot on the right, we represent the data with polar coordinates and the task becomes simple to solve with a vertical line. Figure produced in collaboration with David Warde-Farley.
【极坐标表示数据，可以用垂直线简单地解决这个任务，而笛卡尔坐标无法完成】：假设我们想在散点图中画一条线来分隔两类数据。在左图，我们使用笛卡尔坐标表示数据，这个任务是不可能的。右图中，我们用极坐标表示数据，可以用垂直线简单地解决这个任务。
4、Learned representations often result in much better performance than can be obtained with hand-designed representations. They also allow AI systems to rapidly adapt to new tasks, with minimal human intervention. ？
机器学习到的表 示往往比手动设计的表示表现得更好。
并且它们只需最少的人工干预，就能让AI系 统迅速适应新的任务。
【The quintessential example of a representation learning algorithm is the autoencoder.】 An autoencoder is the combination of an encoder function that converts the input data into a different representation, and a decoder function that converts the new representation back into the original format.
【Autoencoders are trained to preserve as much information as possible when an input is run through the encoder 】 and then the decoder, but are also trained to make the new representation have various nice properties. Different kinds of autoencoders aim to achieve different kinds of properties.
表示学习算法的典型例子是自编码器（autoencoder）。自编码器由一个编码器 （encoder）函数和一个解码器（decoder）函数组合而成。编码器函数将输入数据转 换为一种不同的表示，而解码器函数则将这个新的表示转换到原来的形式。
我们期望当输入数据经过编码器和解码器之后尽可能多地保留信息，同时希望新的表示有 各种好的特性，这也是自编码器的训练目标。为了实现不同的特性，我们可以设计 不同形式的自编码器。
5、A major source of difficulty in many real-world artificial intelligence applications is that 【many of the factors of variation influence every single piece of data we are able to observe. 】？
The individual pixels in an image of a red car might be very close to black at night. The shape of the car’s silhouette depends on the viewing angle. Most applications require us to the factors of variation and discard the disentangle ones that we do not care about.
在许多现实的人工智能应用中，困难主要源于多个变差因素同时影响着我们能 够观察到的每一个数据。
比如，在一张包含红色汽车的图片中，其单个像素在夜间可能会非常接近黑色。汽车轮廓的形状取决于视角。大多数应用需要我们理清变差 因素并忽略我们不关心的因素。
6、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. ？
深度学习（deep learning）通过其他较简单的表示来表达复杂表示，解决了表示学习中的核心问题。
【It is difficult for a computer to understand the meaning of raw sensory input data, such as this image represented as a collection of pixel values.】 The function mapping from a set of pixels to an object identity is very complicated. Learning or evaluating this mapping seems insurmountable if tackled directly.
【breaking the desired complicated mapping into a series of nested simple mappings】：Deep learning resolves this difficulty by breaking the desired complicated mapping into a series of nested simple mappings, each described by a different layer of the model.
计算机难以理解原始感观输入数据的含义，如表示为像素值集合 的图像。将一组像素映射到对象标识的函数非常复杂。如果直接处理，学习或评估此映射似乎是 不可能的。
深度学习将所需的复杂映射分解为一系列嵌套的简单映射（每个由模型的不同层描述） 来解决这一难题。
7、Visible layer (input pixels) to Output (object identity)？
1st hidden layer (edges)
2nd hidden layer (corners and contours)
3rd hidden layer (object parts)
二、内容在总结中
博客对应课程的视频位置：