On-line learning through simple perceptron with a margin

2003/06/05 by Kazuyuki Hara, Masato Okada, Hara, Kazuyuki +1
Computer Science · Physics and Astronomy · #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Physical sciences #Neural Networks and Applications #cond-mat.dis-nn

paper · pdf · doi:10.48550/arxiv.cond-mat/0306150

arxiv created 2003/06/05 · openalex publication_date 2003/06/05 · arxiv updated 2009/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We analyze a learning method that uses a margin κ \it a la Gardner for simple perceptron learning. This method corresponds to the perceptron learning when κ=0, and to the Hebbian learning when κ→ ∞. Nevertheless, we found that the generalization ability of the method was superior to that of the perceptron and the Hebbian methods at an early stage of learning. We analyzed the asymptotic property of the learning curve of this method through computer simulation and found that it was the same as for perceptron learning. We also investigated an adaptive margin control method.

Related

• The Role of Weight Shrinking in Large Margin Perceptron Learning
• The Perceptron with Dynamic Margin
• On-line learning in a discrete state space
• On-line learning with restricted training sets: An exactly solvable case
• A Simple Perceptron that Learns Non-Monotonic Rules