APL descriptions of functional building blocks for connectionist computer models

Authors:
A. Surkan
Affiliations:
Department of Computer Science and Engineering, University of Nebraska, Lincoln, NE
Venue:
APL '89 Conference proceedings on APL as a tool of thought
Year:
1989

Citing 3
Cited 1

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Notation as a tool of thought

Communications of the ACM
Sparse Distributed Memory

Sparse Distributed Memory

Relating number of processing elements in a sparse distributed memory model to learning rate and generalization

APL '91 Proceedings of the international conference on APL '91

Quantified Score

Hi-index	0.00

Visualization

Abstract

APL functions provide concise, array-oriented expressions for describing connection-based computing. These give insights into a variety of neural network-like computer models. Functional decomposition into inherently parallel operation of collective or memory-based computing is effected with the identification of several command-like APL simulation functions.These functions serve to: (a) generate and configure initial values and structures for network layers, connection weights and thresholds, (b) strategically sample training sets to provide acyclic sequences of patterns, (c) update weights for memorizing or learning from the training set, (d) locate units effective for storing and retrieving memories, and (e) use a cue or noise-corrupted pattern for recalling or reconstructing memory associations established during training. Also, APL functions are used to accomodate for data values missing from the training patterns. Other simply described functions generate random fixed reference addresses and initialize modifiable weight values. Test patterns with specified levels of noise contamination are generated by simple APL expressions.