Learn More
Preamble I thank all the individuals involved in the nomination and selection process of IAPR for this honor of the 1992 King-Sun Fu award. In addition, I thank my many collaborators from all over the world over the last three decades, as this award also recognizes their contributions. If memory serves me correctly it was in the early summer of 1961 a(More)
This paper describes an attempt to make use of machine learning or self-organizing processes in the design of a pattern-recognition program. The program starts not only without any knowledge of specific patterns to be input, but also without any operators for processing inputs. Operators are generated and refined by the program itself as a function of the(More)
Massively parallel networks of relatively simple computing elements offer an attractive and versatile framework for exploring a variety of learning structures and processes for intelligent systems. This paper briefly summarizes the popular learning structures and processes used in such networks. It outlines a range of potentially more powerful alternatives(More)
This paper presents and compares results for three types of connectionist networks on perceptual learning tasks: [A] Multi-layered converging networks of neuron-like units, with each unit connected to a small randomly chosen subset of units in the adjacent layers, that learn by re-weighting of their links; [B] Networks of neuron-like units structured into(More)
The absence of powerful control structures and processes that synchronize, coordinate , switch between, choose among, regulate, direct, modulate interactions between, and combine distinct yet interdependent modules of large connectionist networks (CN) is probably one of the most important reasons why such networks have not yet succeeded at handling(More)
The standard heuristic for optimization of network parameters is gradient descent. This heuristic can lead to nonoptimal terminal parameter configurations in multilayer networks. By adding a heuristic that coordinates the development of nearby parameter values, this 'local minimum' problem can be reduced. After motivating the use of local interactions(More)