Incremental Concept Learning via Online Generative Memory Recall

by   Huaiyu Li, et al.

The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts when continually learning new concepts, which is known as catastrophic forgetting problem. The main reason for catastrophic forgetting is that the past concept data is not available and neural weights are changed during incrementally learning new concepts. In this paper, we propose a pseudo-rehearsal based class incremental learning approach to make neural networks capable of continually learning new concepts. We use a conditional generative adversarial network to consolidate old concepts memory and recall pseudo samples during learning new concepts and a balanced online memory recall strategy is to maximally maintain old memories. And we design a comprehensible incremental concept learning network as well as a concept contrastive loss to alleviate the magnitude of neural weights change. We evaluate the proposed approach on MNIST, Fashion-MNIST and SVHN datasets and compare with other rehearsal based approaches. The extensive experiments demonstrate the effectiveness of our approach.


page 1

page 8

page 9


Distillation Techniques for Pseudo-rehearsal Based Incremental Learning

The ability to learn from incrementally arriving data is essential for a...

Convolutional Cobweb: A Model of Incremental Learning from 2D Images

This paper presents a new concept formation approach that supports the a...

Incremental Classifier Learning with Generative Adversarial Networks

In this paper, we address the incremental classifier learning problem, w...

Lifelong Learning Process: Self-Memory Supervising and Dynamically Growing Networks

From childhood to youth, human gradually come to know the world. But for...

Mnemonics Training: Multi-Class Incremental Learning without Forgetting

Multi-Class Incremental Learning (MCIL) aims to learn new concepts by in...

A Unified Framework for Lifelong Learning in Deep Neural Networks

Humans can learn a variety of concepts and skills incrementally over the...

Please sign up or login with your details

Forgot password? Click here to reset