Chapter 10 Information-Theoretic Learning Models 《神经网络与机器学习》 教学课件.pptVIP

Chapter 10 Information-Theoretic Learning Models Figure 10.1 Relationships embodied in the three lines of Eq. (10.32), involving the mutual information I(X; Y). Figure 10.2 Four basic scenarios that lend themselves to the application of information maximization and its three variants. Figure 10.3 Signal-flow graph of a noisy neuron. Figure 10.4 Another noisy model of the neuron. Figure 10.5 Model of a perceptual system. The signal vector s and noise vectors vi and vo are values of the random vectors S, Ni, and No, respectively. Figure 10.6 Processing of two neighboring regions of a