Tham khảo tài liệu 'artificial mind system – kernel memory approach - tetsuya hoya part 11', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | 126 7 Learning in the AMS Context weights with having their template vectors defined in a different dimensionality to represent other modality. Then during the learning process the respective sub-SOKMs can be reconfigured within the so-called competitive learning principle for the general notion see von der Malsburg 1973 4 to be described later. The Unit for Performing the Reinforcement Learning Unit 5 As aforementioned Unit 5 sends the reinforcement signals to reconfigure the units 1 -4 . In this example for simplicity it is assumed that the reinforcement signals are given . based upon the statistics of the errors between the pattern recognition results and externally provided or pre-determined target responses as in ordinary ANN approaches. In such a case the comparator denoted by C in the circle in Fig. can be replaced with a simple operator that yields the error. However within a more general context of reinforcement learning as described in Sect. the target responses or reinforcement signals can be given as the outcome from the interactive processes between the modules within the AMS. Competitive Learning of the Sub-Systems Without loss of generality5 as shown in Fig. consider that the combined self-evolutionary feature extraction and pattern recognition system which is responsible for a particular domain of sensory data . for a single cate-gory modality consists of the two partially distinct sub-systems A and B. Then suppose that the respective feature extraction . Units 1 -3 and pattern classification parts . Unit 4 are configured with two distinct parameter sets A and B . both feature extraction A and sub-SOKM A have been configured with parameter set A during a certain period of time P1 whereas both feature extraction B and sub-SOKM B have been formed with parameter set B during the period p2 and that both the sub-systems are working in parallel. Based upon the error generated from the comparator C1 attached to both .
