IEEE (Institute of Electrical and Electronic Engineers) Conference on Neural Information Processing Systems - Natural and Synthetic Held in Denver, Colorado on November 8-12, 1987. Abstracts of Papers.

摘要

Contents: Bifurcation analysis of a network model of a rabbit olfactory bulb with periodic attractors stored by a sequence learning algorithm; Model of the cerebellum as an array of adjustable pattern generators; Spontaneous and information-triggered segments of series of human brain electric field maps; Towards an organizing principle for perception: The role of Hebbian synapses in the emergence of feature-analyzing function; Synchronization in neural nets; New neural algorithms for associative memory; A neural network classifier based on coding theory; A trellis-structured neural network; Minkowski-r back-propagation: Learning in connectionist models with non-euclidian error signals; Generalization of back-propagation to recurrent and high-order networks; Partitioning of sensory data by a cortical network; The generation of efficient representations in neural net architectures using high order correlations; Learning representations by recirculation; Strategies for teaching layered networks classification tasks; Stochastic learning networks and their electronic implementation; Speech stabilization and robots front ends for neural networks; Genetic database analysis with neural nets; Dynamical neural networks and their application to robot control; Simulations suggest information processing roles for the diverse currents found the Hippocampal neurons; A computer simulation of cerebral neocortex: Computational capabilities of nonlinear networks; An adaptive and heterodyne filtering procedure for the imaging of moving objects; Phase transitions in neural networks. (jhd)