paper-with-me

홈 › Papers

Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks

2018-02-12 · Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony Robins

In general, neural networks are not currently capable of learning tasks in a sequential fashion. When a novel, unrelated task is learnt by a neural network, it substantially forgets how to solve previously learnt tasks. One of the original solutions to this problem is pseudo-rehearsal, which involves learning the new task while rehearsing generated items representative of the previous task/s. This is very effective for simple tasks. However, pseudo-rehearsal has not yet been successfully applied to very complex tasks because in these tasks it is difficult to generate representative items. We accomplish pseudo-rehearsal by using a Generative Adversarial Network to generate items so that our deep network can learn to sequentially classify the CIFAR-10, SVHN and MNIST datasets. After training on all tasks, our network loses only 1.67% absolute accuracy on CIFAR-10 and gains 0.24% absolute accuracy on SVHN. Our model's performance is a substantial improvement compared to the current state of the art solution.

📄 PDF Abstract BibTeX arXiv:1802.03875

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial Network

Similar Papers 제목 키워드 기반

Catastrophic Importance of Catastrophic Forgetting

2018-08-20 · Albert Ierusalem

This paper describes some of the possibilities of artificial neural networks that open up after solving the problem of catastrophic forgetting. A simple model and reinforcement learning applications of existing methods a…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting

2018-12-06 · Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony Robins

Neural networks can achieve excellent results in a wide variety of applications. However, when they attempt to sequentially learn, they tend to learn the new task while catastrophically forgetting previous ones. We propo…

Atari GamesContinual LearningDeep Reinforcement Learningimage-classification+4

Reminding the Incremental Language Model via Data-Free Self-Distillation

2021-10-17 · Han Wang, Ruiliu Fu, Chengzhang Li, Xuejun Zhang 외

Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. Th…

Data AugmentationLanguage ModelingLanguage Modelling

Pseudorehearsal in actor-critic agents with neural network function approximation

2017-12-20 · Vladimir Marochko, Leonard Johard, Manuel Mazzara, Luca Longo

Catastrophic forgetting has a significant negative impact in reinforcement learning. The purpose of this study is to investigate how pseudorehearsal can change performance of an actor-critic agent with neural-network fun…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Knowledge Restore and Transfer for Multi-label Class-Incremental Learning

2023-02-26 · ICCV 2023 1 · Songlin Dong, Haoyu Luo, Yuhang He, Xing Wei 외

Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied. Although t…

class-incremental learningClass Incremental LearningIncremental LearningPseudo Label