Skip to Main content Skip to Navigation
Conference papers

Fast Training and Efficient Linear Learning Machine

Abdenour Bounsiar 1 Pierre Beauseroy 1 Edith Grall-Maës 1
1 M2S - Modélisation et Sûreté des Systèmes
ISTIT - Institut des Sciences et Technologies de l'Information de Troyes
Abstract : Time complexity is a challenge for learning machines. In this paper, a fast training and efficient linear learning machine is presented. Starting from a simple linear classifier, a new one is proposed based on an improvement on the first one. The machine obtained is characterized by a weight vector that can be processed immediately without any complex calculus or optimization step, which allows for considerable training time savings. A geometric interpretation of the proposed method is given. Experiments show that this classifier is competitive to other state of the art linear learning methods such as support vector machines and kernel Fisher discriminant
Complete list of metadatas

https://hal-utt.archives-ouvertes.fr/hal-02317717
Contributor : Jean-Baptiste Vu Van <>
Submitted on : Wednesday, October 16, 2019 - 11:53:07 AM
Last modification on : Wednesday, May 20, 2020 - 11:34:05 AM

Identifiers

Collections

CNRS | UTT

Citation

Abdenour Bounsiar, Pierre Beauseroy, Edith Grall-Maës. Fast Training and Efficient Linear Learning Machine. 2006 IEEE International Conference on Acoustics Speed and Signal Processing, May 2006, Toulouse, France. pp.V-777-V-780, ⟨10.1109/ICASSP.2006.1661391⟩. ⟨hal-02317717⟩

Share

Metrics

Record views

26