Deep Incremental Boosting

TL;DR

Deep Incremental Boosting is a novel ensemble technique for deep learning that reduces training time and enhances generalization by leveraging transfer learning for incremental ensemble training.

Contribution

It introduces a new boosting method tailored for deep learning that incorporates transfer learning to accelerate training of ensemble members.

Findings

Reduces training time for deep ensemble models.

Improves generalization performance on standard datasets.

Preliminary results show promising potential for deep learning applications.

Abstract

This paper introduces Deep Incremental Boosting, a new technique derived from AdaBoost, specifically adapted to work with Deep Learning methods, that reduces the required training time and improves generalisation. We draw inspiration from Transfer of Learning approaches to reduce the start-up time to training each incremental Ensemble member. We show a set of experiments that outlines some preliminary results on some common Deep Learning datasets and discuss the potential improvements Deep Incremental Boosting brings to traditional Ensemble methods in Deep Learning.