Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkSimilar Papers 제목 키워드 기반
Catastrophic Importance of Catastrophic Forgetting
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
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+4Reminding the Incremental Language Model via Data-Free Self-Distillation
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 ModellingPseudorehearsal in actor-critic agents with neural network function approximation
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
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