Linear function neurons: Structure and training

DOI10.1007/BF00336991MaRDI QIDQ1070193zbMATH OpenOpenAlexWikidataFDO

Authors Steven Hampson, Dennis James Volper

Publication date 1986

Published in Biological Cybernetics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/bf00336991

zbMATH Keywords

animal learningAplysia gill withdrawalbinary inputneural learningperceptron trainingRescorla-Wagner learningtraining algorithm for linear equations

Mathematics Subject Classification ID

Physiological, cellular and medical topics (92Cxx) Other natural sciences (mathematical treatment) (92F05)

Review text

Three different representations for a thresholded linear equation are developed. For binary input they are shown to be representationally equivalent though their training characteristics differ. A training algorithm for linear equations is discussed. The similarities between its simplest mathematical representation (perceptron training), a formal model of animal learning (Rescorla-Wagner learning), and one mechanism of neural learning (Aplysia gill withdrawal) are pointed out.

Recommendations

• Representing and learning Boolean functions of multivalued features
• Learning algorithms based on linearization
• A generalized algorithm of training a formal neuron
• Multiple threshold perceptron
• Directed drift: A new linear threshold algorithm for learning binary weights on-line

Cites work

• A Boolean complete neural model of adaptive behavior
• A logical calculus of the ideas immanent in nervous activity
• Associative search network: A reinforcement learning associative memory
• Dynamics of pattern formation in lateral-inhibition type neural fields
• scientific article; zbMATH DE number 3436645 (Why is no real title available?)
• scientific article; zbMATH DE number 3214054 (Why is no real title available?)
• scientific article; zbMATH DE number 3266648 (Why is no real title available?)
• scientific article; zbMATH DE number 3385535 (Why is no real title available?)
• Landmark learning: An illustration of associative search
• Lower Bound of the Number of Threshold Functions
• Neural theory of association and concept-formation
• On Complete Sets of Logic Primitives
• Punish/Reward: Learning with a Critic in Adaptive Threshold Systems
• The human brain, social conformity, and presidential elections
• The Relaxation Method for Linear Inequalities

Cited in

(9)

• Connectionistic models of Boolean category representation
• Disjunctive models of Boolean category learning
• A parallel network that learns to play backgammon
• A generalized algorithm of training a formal neuron
• On specifying Boolean functions by labelled examples
• Improved approximation of linear threshold functions
• scientific article; zbMATH DE number 4123585 (Why is no real title available?)
• Using the Perceptron Algorithm to Find Consistent Hypotheses
• Progress in Artificial Intelligence

This page was built for publication: Linear function neurons: Structure and training

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1070193)