PDE Seminar (2018/10/26): 適応フィルタが創発する自己組織化マップとそのデモンストレーション

2018-10-26 16:30 - 2018-10-26 18:00
Faculty of Science Building #3, Room 309
Hideo Kubo (Hokkaido University), Kogo Yoshikawa (Hokkaido University)
For the modeling of the brain, the adaptive filter is introduced by Kohonen. It is a frame allowing for elementary operation to change with time, and this is described by the differential equation basically. Furthermore, the order by a certain measure among input data can be almost preserved about the order by other measure among output data, if we introduce mechanism of the lateral interaction into adaptive filters. The order to occur in this way is known as Self-Organizing Map (SOM). We will show a computer demo playing SOM software with a toy problem. The software implementation of SOM represents the result of a vector quantization algorithm that places a number of reference or codebook vectors into a high-dimensional input data space to approximate to its data sets in an ordered fashion. This demo would help us to understand why and how SOM works.