On the Classification Capability of Sign-Constrained Perceptrons

DOI10.1162/NECO.2008.20.1.288MaRDI QIDQ3539965zbMATH OpenOpenAlexWikidataFDO

Authors Robert A. Legenstein, Wolfgang Maass

Publication date 19 November 2008

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco.2008.20.1.288

Mathematics Subject Classification ID

Neural biology (92C20)

Recommendations

• scientific article; zbMATH DE number 4204162
• A survey of constrained classification
• On some universal constraints for classification algorithms
• Saturated perceptrons for maximum margin and minimum misclassification error
• Exploiting layerwise convexity of rectifier networks with sign constrained weights
• Class sparsity signature based restricted Boltzmann machine

Cites work

• A logical calculus of the ideas immanent in nervous activity
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• The interaction space of neural networks with sign-constrained synapses
• The space of interactions in neural network models

Cited in

(7)

• Implementation of multilayer perceptron networks by populations of spiking neurons using rate coding
• Supervised learning with decision margins in pools of spiking neurons
• Binary classifiers, perceptrons and connectedness in metric spaces and graphs
• Maintaining consistency of spatial information in the hippocampal network: a combinatorial geometry model
• Positive neural networks in discrete time implement monotone-regular behaviors
• Exploiting layerwise convexity of rectifier networks with sign constrained weights
• Learning to discriminate through long-term changes of dynamical synaptic transmission

This page was built for publication: On the Classification Capability of Sign-Constrained Perceptrons

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3539965)