The brain-state-in-a-box neural model is a gradient descent algorithm

DOI10.1016/0022-2496(86)90043-XzbMath0587.92028MaRDI QIDQ1072966

Richard M. Golden

Publication date: 1986

Published in: Journal of Mathematical Psychology (Search for Journal in Brave)

zbMATH Keywords

Lyapunov functionneurophysiologyquadratic cost functionbrain-state-in-a-box (BSB) neural modelconstrained gradient descent algorithmexistence of global energy minimasystem equilibrium points

Mathematics Subject Classification ID

Nonlinear programming (90C30) Psychophysics and psychophysiology; perception (91E30) Mathematical psychology (91E99) Physiological, cellular and medical topics (92Cxx)

Related Items (7)

SYNCHRONOUS AND ASYNCHRONOUS BRAIN-STATE-IN-A-BOX INFORMATION SYSTEM NEURAL MODELS ⋮ A unified framework for connectionist systems ⋮ Symbolic functions from neural computation ⋮ Adaptive learning of fuzzy BSB and GBSB neural models ⋮ Neural network approach to firm grip in the presence of small slips ⋮ Optimal and robust design of brain-state-in-a-box neural associative memories ⋮ The BSB neural network in the convex body spanned by the prototype patterns for associative memory

Cites Work

• Unnamed Item
• Unnamed Item
• An approach to nonlinear programming
• On the Foundations of Relaxation Labeling Processes
• <tex>L_infty</tex>-stability criteria for interconnected systems using exponential weighting
• Neurons with graded response have collective computational properties like those of two-state neurons.

This page was built for publication: The brain-state-in-a-box neural model is a gradient descent algorithm