AI_chapter3.pptVIP

Chapter 3 Neural Networks Discuss methods by which machines can learn As an example, how the action-selecting computations performed by S-R machines can be learned through exposure to a set of samples of inputs paired with the action that would be appropriate for each input. Networks of TLUs with adjustable weights are concerned here. Learning is achieved by adjusting the weights in the network until its action-computing performance is acceptable. (网络系统通过调节权值直到获得令人满意的动作计算性能来进行学习。) Machine Learning Problem Learning problem description Given a set of n-dimensional vector