《超越学科的认知基础》2015秋刘诗宇学习报告

课堂感想 上完第一节课的最大感想就是：原来还有这么多有意思的东西我从来没有听说过。能和很多在科研思想上有见地的老师交流，也是非常难得的机会。初识很多软件应用以及阅读大量英文专业文献对我来说也算是不小的挑战。希望能够在这一学期的学习中收获超越学科的认知体验。

比较分析 Probably approximately correct THE MATHEMATICAL THEORY OF COMMUNICATION 对常规语义的扩充 ecorithms :Unlike most algorithms, they can be run in environments unknown to the designer, and they learn by interacting with the environment how to act effectively in it. After sufficient interaction they will have expertise not provided by the designer, but extracted from the environment. The model of learning they follow, known as the probably approximately correct model, provides a quantitative framework in which designers can evaluate the expertise achieved and the cost of achieving it. Communication : The word communication will be used here in a very broad sense to include all of the procedures by which one mind may affect another. This, of course, involves not only written and oral speech, but also music, the pictorial arts, the theatre, the ballet, and in fact all human behavior. In some connections it may be desirable to use a still broader definition of communication, namely, one which would include the procedures by means of which one mechanism (say automatic equipment to track an airplane and to compute its probable future positions) affects another mechanism (say a guided missile chasing this airplane). 对讨论对象的分类 Theoryful & Theoryless Those aspects of knowledge for which there is a good predictive theory, typically a mathematical or scientific one, will be called theoryful. The rest will be called theoryless. The notions of the theoryful and the theoryless as used here are relative, relative to the knowledge of the decision maker in question. While gravity and mechanics may be theoryful to a physicist, they will not be to a fish or a bird, which still have to cope with the physical world, but do so, we presume, without following a theory. Three Levels of Communications Problems Relative to the broad subject of communication, there seem to be problems at three levels. Thus it seems reasonable to ask, serially: LEVEL A. How accurately can the symbols of communication be transmitted? (The technical problem.) LEVEL B. How precisely do the transmitted symbols convey the desired meaning? (The semantic problem.) LEVEL C. How effectively does the received meaning affect conduct in the desired way? (The effectiveness problem.) 对前人理论的发展 Hence the right goal must be to find a mathematical definition of learning of a nature similar to Turing’s notion of computation, rather than an 15/233 informal notion like the Turing Test. At the heart of my thesis here is a mathematical definition of learning. It is called the PAC or the probably approximately correct model of learning. The mathematical theory of the engineering aspects of communication, as developed chiefly by Claude Shannon at the Bell Telephone Laboratories, admittedly applies in the first instance only to problem A, namely, the technical problem of accuracy of transference of various types of signals from sender to receiver. But the theory has, I think, a deep significance which proves that the preceding paragraph is seriously inaccurate. Part of the significance of the new theory comes from the fact that levels Band C, above, can make use only of those signal accuracies which turn out to be possible when analyzed at Level A. Thus any limitations discovered in the theory at Level A necessarily apply to levels Band C. 关键人物 John von Neumann, Turing Claude Shannon 关键机构 the Association for Computing Machinery the Bell Telephone Laboratories