Presentation 2001/6/21
Learning of several signal sources using a Learning Vector Quantization with variable receptive field.
Nobufusa Kobayashi, Koichiro Yamauchi, Takashi Omori,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Almost all of the conventional learning systems are designed to learn signals from a single data-source. However, in real world, the high dimensional inputs given to the learning system include several data-sources. The high-dimensional inputs are varied by the combination of those signal sources, each of which yields its own signals independently. This means that there are a large number of variation in the inputs. Therefore, if we apply the conventional learning methods for the learning of such inputs, the learning system cannot memorize all of them quantization method, which deceomposes independent data-sources and learns each data-source separately. In the new method, the LVQ dose not memorize the combination of the signals from the data-sourecs, so that the system memorizes them using a small amount of resources.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Learning Vector Quantization(LVQ) / Self-organization / Decomposition of Inputs / Variable Receptive Field
Paper # NC2001-20
Date of Issue

Conference Information
Committee NC
Conference Date 2001/6/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning of several signal sources using a Learning Vector Quantization with variable receptive field.
Sub Title (in English)
Keyword(1) Learning Vector Quantization(LVQ)
Keyword(2) Self-organization
Keyword(3) Decomposition of Inputs
Keyword(4) Variable Receptive Field
1st Author's Name Nobufusa Kobayashi
1st Author's Affiliation Graduate School of Engineering, Hokkaido University()
2nd Author's Name Koichiro Yamauchi
2nd Author's Affiliation Graduate School of Engineering, Hokkaido University
3rd Author's Name Takashi Omori
3rd Author's Affiliation Graduate School of Engineering, Hokkaido University
Date 2001/6/21
Paper # NC2001-20
Volume (vol) vol.101
Number (no) 153
Page pp.pp.-
#Pages 7
Date of Issue