Noise Robust Gradient Descent Learning for Complex-Valued Associative Memory

スポンサーリンク

概要

• 論文の詳細を見る

• Complex-valued Associative Memory (CAM) is an advanced model of Hopfield Associative Memory. The CAM is based on multi-state neurons and has the high ability of representation. Lee proposed gradient descent learning for the CAM to improve the storage capacity. It is based on only the phases of input signals. In this paper, we propose another type of gradient descent learning based on both the phases and the amplitude. The proposed learning method improves the noise robustness and accelerates the learning speed.

• （社）電子情報通信学会の論文
• 2011-08-01

著者

• Kobayashi Masaki

  Interdisciplinary Graduate School Of Medicine And Engineering University Of Yamanashi

• Kitahara Michimasa

  Interdisciplinary Graduate School Of Medicine And Engineering University Of Yamanashi

• YAMADA Hirofumi

  Interdisciplinary Graduate School of Medicine and Engineering, University of Yamanashi

• Kobayashi Masaki

  Interdisciplinary Graduate School Of Medicine And Engineering Univ. Of Yamanashi

• Yamada Hirofumi

  Interdisciplinary Graduate School Of Medicine And Engineering University Of Yamanashi

関連論文

• Boltzmann Machines with Identified States
• Noise Robust Gradient Descent Learning for Complex-Valued Associative Memory

スポンサーリンク