Presentation 2022-11-17
A clustering system based on binary associative memories
Kazuma Kiyohara, Kento Saka, Toshimichi Saito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper studies application of binary associative memories to clustering systems of binary data. The binary associative memories are simple recurrent neural networks characterized by ternary connection parameters and the signum activation function. Applying correlation based learning, storage of any set of desired memories are guaranteed. In the application, clusters are given by initial points falling into desired memories and spurious memories. Using simple example problem, basic clustering functions are investigated.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Binary neural networks / associative memories / clustering
Paper # CCS2022-43
Date of Issue 2022-11-10 (CCS)

Conference Information
Committee CCS
Conference Date 2022/11/17(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Megumi Akai(Hokkaido Univ.)
Vice Chair Hidehiro Nakano(Tokyo City Univ.) / Masaki Aida(TMU)
Secretary Hidehiro Nakano(Shibaura Inst. of Tech.) / Masaki Aida(Mie Univ.)
Assistant Hiroyuki Yasuda(Univ. of Tokyo) / Hiroyasu Ando(Tsukuba Univ.) / Tomoyuki Sasaki(Shonan Inst. of Tech.) / Miki Kobayashi(Rissho Univ.)

Paper Information
Registration To Technical Committee on Complex Communication Sciences
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A clustering system based on binary associative memories
Sub Title (in English)
Keyword(1) Binary neural networks
Keyword(2) associative memories
Keyword(3) clustering
1st Author's Name Kazuma Kiyohara
1st Author's Affiliation HOSEI Univerisity(HU)
2nd Author's Name Kento Saka
2nd Author's Affiliation HOSEI Univerisity(HU)
3rd Author's Name Toshimichi Saito
3rd Author's Affiliation HOSEI Univerisity(HU)
Date 2022-11-17
Paper # CCS2022-43
Volume (vol) vol.122
Number (no) CCS-255
Page pp.pp.1-4(CCS),
#Pages 4
Date of Issue 2022-11-10 (CCS)