Learning the pseudoinverse solution to network weights

DOI10.1016/j.neunet.2013.02.008zbMath1296.68147arXiv1207.3368OpenAlexW2138061685WikidataQ44291854 ScholiaQ44291854MaRDI QIDQ460784

J. Tapson, André van Schaik

Publication date: 9 October 2014

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1207.3368

zbMATH Keywords

Moore-Penrose pseudoinverseextreme learning machinebiological plausibilityneural engineering

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items (5)

Pseudo-inverse linear discriminants for the improvement of overall classification accuracies ⋮ Impact of random weights on nonlinear system identification using convolutional neural networks ⋮ STICK: Spike Time Interval Computational Kernel, a Framework for General Purpose Computation Using Neurons, Precise Timing, Delays, and Synchrony ⋮ Storing cycles in Hopfield-type networks with pseudoinverse learning rule: admissibility and network topology ⋮ Randomized algorithms for nonlinear system identification with deep learning modification

Uses Software

• MNIST

Cites Work

• Self-organization and associative memory
• Generalized inverses. Theory and applications.
• Large-Margin Classification in Infinite Neural Networks
• Oscillation and Chaos in Physiological Control Systems
• Some Applications of the Pseudoinverse of a Matrix
• Correlation Matrix Memories
• Unnamed Item
• Unnamed Item

This page was built for publication: Learning the pseudoinverse solution to network weights