Variational Learning for Multi-Layer Networks of Linear Threshold Units

Neil D. Lawrence
Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, PMLR R3:168-175, 2001.

Abstract

Linear threshold units (LTUs) were originally proposed as models of biological neurons. They were widely studied in the context of the perceptron (Rosenblatt, 1962). Due to the difficulties of finding a general algorithm for networks with hidden nodes, they never passed into general use. In this work we derive an algorithm in the context of probabilistic models and show how it may be applied in multi-layer networks of LTUs. We demonstrate the performance of the algorithm on three data-sets.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR3-lawrence01a, title = {Variational Learning for Multi-Layer Networks of Linear Threshold Units}, author = {Lawrence, Neil D.}, booktitle = {Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics}, pages = {168--175}, year = {2001}, editor = {Richardson, Thomas S. and Jaakkola, Tommi S.}, volume = {R3}, series = {Proceedings of Machine Learning Research}, month = {04--07 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r3/lawrence01a/lawrence01a.pdf}, url = {https://proceedings.mlr.press/r3/lawrence01a.html}, abstract = {Linear threshold units (LTUs) were originally proposed as models of biological neurons. They were widely studied in the context of the perceptron (Rosenblatt, 1962). Due to the difficulties of finding a general algorithm for networks with hidden nodes, they never passed into general use. In this work we derive an algorithm in the context of probabilistic models and show how it may be applied in multi-layer networks of LTUs. We demonstrate the performance of the algorithm on three data-sets.}, note = {Reissued by PMLR on 31 March 2021.} }
Endnote
%0 Conference Paper %T Variational Learning for Multi-Layer Networks of Linear Threshold Units %A Neil D. Lawrence %B Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2001 %E Thomas S. Richardson %E Tommi S. Jaakkola %F pmlr-vR3-lawrence01a %I PMLR %P 168--175 %U https://proceedings.mlr.press/r3/lawrence01a.html %V R3 %X Linear threshold units (LTUs) were originally proposed as models of biological neurons. They were widely studied in the context of the perceptron (Rosenblatt, 1962). Due to the difficulties of finding a general algorithm for networks with hidden nodes, they never passed into general use. In this work we derive an algorithm in the context of probabilistic models and show how it may be applied in multi-layer networks of LTUs. We demonstrate the performance of the algorithm on three data-sets. %Z Reissued by PMLR on 31 March 2021.
APA
Lawrence, N.D.. (2001). Variational Learning for Multi-Layer Networks of Linear Threshold Units. Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R3:168-175 Available from https://proceedings.mlr.press/r3/lawrence01a.html. Reissued by PMLR on 31 March 2021.

Related Material