Learning and Generalization with Minimerror, a Temperature-Dependent Learning Algorithm

Raffin, Bruno; Gordon, Mirta B.

doi:10.1162/NECO.1995.7.6.1206

Learning and Generalization with Minimerror, a Temperature-Dependent Learning Algorithm

Bruno Raffin, Mirta B. Gordon

NeCo 1995 pp. 1206-1224

doi:10.1162/NECO.1995.7.6.1206 /neco/1995/raffin1995neco-learning/

Abstract

We study the numerical performances of Minimerror, a recently introduced learning algorithm for the perceptron that has analytically been shown to be optimal both on learning linearly and nonlinearly separable functions. We present its implementation on learning linearly separable boolean functions. Numerical results are in excellent agreement with the theoretical predictions.

NeCo Semantic Scholar

Cite

Text

Raffin and Gordon. "Learning and Generalization with Minimerror, a Temperature-Dependent Learning Algorithm." Neural Computation, 1995. doi:10.1162/NECO.1995.7.6.1206

Markdown

[Raffin and Gordon. "Learning and Generalization with Minimerror, a Temperature-Dependent Learning Algorithm." Neural Computation, 1995.](https://mlanthology.org/neco/1995/raffin1995neco-learning/) doi:10.1162/NECO.1995.7.6.1206

BibTeX

@article{raffin1995neco-learning,
  title     = {{Learning and Generalization with Minimerror, a Temperature-Dependent Learning Algorithm}},
  author    = {Raffin, Bruno and Gordon, Mirta B.},
  journal   = {Neural Computation},
  year      = {1995},
  pages     = {1206-1224},
  doi       = {10.1162/NECO.1995.7.6.1206},
  volume    = {7},
  url       = {https://mlanthology.org/neco/1995/raffin1995neco-learning/}
}