Power Law Slowdown of the Neural Learning

スポンサーリンク

概要

• 論文の詳細を見る

• We numerically show that the learning time t of the back propagation model with the encoder topology obeys a power law described as t ∝ M^D(D : constant, 1 < D ≲ 2), with M being the number of input patterns.

• 社団法人電子情報通信学会の論文
• 1994-12-25

著者

• Fuchikami Nobuko

  Faculty Of Science Tokyo Metropolitan University

• Nakajima Tatsuhiro

  Faculty Of Science Tokyo Metropolitan University

• Nakajima Tatsuhiro

  Faculty Of Economics Meikai University

• Cateau Hideyuki

  Laboratory for Neural Modeling, Institute of Physical and Chemical Science Research (RIKEN)

• Nunokawa Hiroshi

  National Laboratory for High Energy Physics (KEK)

• Cateau H

  Laboratory For Neural Modeling Institute Of Physical And Chemical Science Research (riken)

• Nunokawa H

  Japan Atomic Energy Res. Inst. Ibaraki

関連論文

• Generalized Cyclic Characters of Symmetric Groups
• MECHANISM OF LIPID LATERAL DIFFUSION IN LIPID BILAYER MEMBRANES
• Power Law Slowdown of the Neural Learning
• On reduced Q-functions

スポンサーリンク