12.7. Neural Network Implementation
In this section, a neural network architecture is introduced and is then used to implement BSAS.
12.7.1. Description of the Architecture
The architecture is shown in Figure 12.4a. It consists of two modules, the matching score generator (MSG) and the MaxNet network (MN).[4]
4 This is a generalization of the Hamming network proposed in [Lipp 87].
FIGURE 12.4. (a) The neural architecture. (b) Implementation of the BSAS algorithm when each cluster is represented by its mean vector and the Euclidean distance between two vectors is used.
The first module stores q parameter vectors[5]W1, w2,…,wq of dimension ...
Get Pattern Recognition, 4th Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
