Overcoming catastrophic forgetting in neural networks
James Kirkpatrick,Razvan Pascanu,Neil C. Rabinowitz,Joel Veness,Guillaume Desjardins,Andrei Rusu,Kieran Milan,John Quan,Tiago Ramalho,Agnieszka Grabska-Barwinska,Demis Hassabis,Claudia Clopath,Dharshan Kumaran,Raia Hadsell +13 more
TL;DR: In this paper, the authors show that it is possible to train networks that can maintain expertise on tasks that they have not experienced for a long time by selectively slowing down learning on the weights important for those tasks.
read more
Abstract: The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Until now neural networks have not been capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is possible to overcome this limitation and train networks that can maintain expertise on tasks that they have not experienced for a long time. Our approach remembers old tasks by selectively slowing down learning on the weights important for those tasks. We demonstrate our approach is scalable and effective by solving a set of classification tasks based on a hand-written digit dataset and by learning several Atari 2600 games sequentially.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
Deep Reinforcement Learning: An Overview
TL;DR: This work discusses core RL elements, including value function, in particular, Deep Q-Network (DQN), policy, reward, model, planning, and exploration, and important mechanisms for RL, including attention and memory, unsupervised learning, transfer learning, multi-agent RL, hierarchical RL, and learning to learn.
•Posted Content
FiLM: Visual Reasoning with a General Conditioning Layer
TL;DR: Feature-wise linear modulation (FiLM) as mentioned in this paper is a general-purpose conditioning method for neural networks, which can influence neural network computation via a simple, feature-wise affine transformation based on conditioning information.
1.2K
Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications
TL;DR: A survey of different approaches to problems related to multiagent deep RL (MADRL) is presented, including nonstationarity, partial observability, continuous state and action spaces, multiagent training schemes, and multiagent transfer learning.
1K
•Posted Content
Efficient Lifelong Learning with A-GEM
TL;DR: An improved version of GEM is proposed, dubbed Averaged GEM (A-GEM), which enjoys the same or even better performance as GEM, while being almost as computationally and memory efficient as EWC and other regularization-based methods.
1K
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Samuel Gehman,Suchin Gururangan,Maarten Sap,Yejin Choi,Noah A. Smith +4 more
- 01 Nov 2020
TL;DR: It is found that pretrained LMs can degenerate into toxic text even from seemingly innocuous prompts, and empirically assess several controllable generation methods find that while data- or compute-intensive methods are more effective at steering away from toxicity than simpler solutions, no current method is failsafe against neural toxic degeneration.
References
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
67K
Human-level control through deep reinforcement learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Andrei Rusu,Joel Veness,Marc G. Bellemare,Alex Graves,Martin Riedmiller,Andreas K. Fidjeland,Georg Ostrovski,Stig Petersen,Charles Beattie,Amir Sadik,Ioannis Antonoglou,Helen King,Dharshan Kumaran,Daan Wierstra,Shane Legg,Demis Hassabis +18 more
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
An integrative theory of prefrontal cortex function
Earl K. Miller,Jonathan D. Cohen +1 more
TL;DR: It is proposed that cognitive control stems from the active maintenance of patterns of activity in the prefrontal cortex that represent goals and the means to achieve them, which provide bias signals to other brain structures whose net effect is to guide the flow of activity along neural pathways that establish the proper mappings between inputs, internal states, and outputs needed to perform a given task.
Deep reinforcement learning with double Q-learning
H Van Hasselt,Arthur Guez,David Silver +2 more
- 01 Jan 2015
TL;DR: In this article, the authors show that the DQN algorithm suffers from substantial overestimation in some games in the Atari 2600 domain, and they propose a specific adaptation to the algorithm and show that this algorithm not only reduces the observed overestimations, but also leads to much better performance on several games.
7.9K