Least Squares Maximum and Weighted Generalization-Memorization Machines

TL;DR

This paper introduces memory influence mechanisms for least squares support vector machines, enhancing generalization and efficiency without altering original constraints, through the proposed MIMM and WIMM models.

Contribution

It presents novel memory impact models (MIMM and WIMM) that improve generalization and reduce computational cost in LSSVM without changing its fundamental constraints.

Findings

MIMM and WIMM outperform LSSVM in generalization

Models significantly reduce time costs

Memory impact functions enhance partitioning accuracy

Abstract

In this paper, we propose a new way of remembering by introducing a memory influence mechanism for the least squares support vector machine (LSSVM). Without changing the equation constraints of the original LSSVM, this mechanism, allows an accurate partitioning of the training set without overfitting. The maximum memory impact model (MIMM) and the weighted impact memory model (WIMM) are then proposed. It is demonstrated that these models can be degraded to the LSSVM. Furthermore, we propose some different memory impact functions for the MIMM and WIMM. The experimental results show that that our MIMM and WIMM have better generalization performance compared to the LSSVM and significant advantage in time cost compared to other memory models.