A "Thermal" Perceptron Learning Rule
Abstract
The thermal perceptron is a simple extension to Rosenblatt's perceptron learning rule for training individual linear threshold units. It finds stable weights for nonseparable problems as well as separable ones. Experiments indicate that if a good initial setting for a temperature parameter, T0, has been found, then the thermal perceptron outperforms the Pocket algorithm and methods based on gradient descent. The learning rule stabilizes the weights (learns) over a fixed training period. For separable problems it finds separating weights much more quickly than the usual rules.
Cite
Text
Frean. "A "Thermal" Perceptron Learning Rule." Neural Computation, 1992. doi:10.1162/NECO.1992.4.6.946Markdown
[Frean. "A "Thermal" Perceptron Learning Rule." Neural Computation, 1992.](https://mlanthology.org/neco/1992/frean1992neco-thermal/) doi:10.1162/NECO.1992.4.6.946BibTeX
@article{frean1992neco-thermal,
title = {{A "Thermal" Perceptron Learning Rule}},
author = {Frean, Marcus R.},
journal = {Neural Computation},
year = {1992},
pages = {946-957},
doi = {10.1162/NECO.1992.4.6.946},
volume = {4},
url = {https://mlanthology.org/neco/1992/frean1992neco-thermal/}
}