Abstract
Neural networks can achieve extraordinary results on a wide variety of tasks. However, when they attempt to sequentially learn a number of tasks, they tend to learn the new task while destructively forgetting previous tasks. This is known as the Catastrophic Forgetting problem and it is an essential
problem to solve if we want to achieve artificial agents that can continuously learn. This project aims to solve Catastrophic Forgetting by having the network rehearse previous tasks while learning new ones. Previous tasks are rehearsed from examples produced by a single generative model that is also sequentially trained on all previously learnt tasks.
Related Publications
C. Atkinson, B. McCane, L. Szymanski and A. Robins. Pseudo-rehearsal: Achieving deep reinforcement learning without catastrophic forgetting. Neurocomputing, 428:291 - 307, 2021.
@article{atkinson2020pseudo,
title = "Pseudo-rehearsal: Achieving deep reinforcement learning without catastrophic forgetting",
journal = "Neurocomputing",
volume = "428",
pages = "291 - 307",
year = "2021",
issn = "0925-2312",
doi = "https://doi.org/10.1016/j.neucom.2020.11.050",
url = "http://www.sciencedirect.com/science/article/pii/S0925231220318439",
author = "Craig Atkinson and Brendan McCane and Lech Szymanski and Anthony Robins",
}
Bibtex has been copied to clipboard.
Bibtex has been copied to clipboard.
C. Atkinson, B. McCane, L. Szymanski and A. Robins. GRIm-RePR: Prioritising Generating Important Features for Pseudo-Rehearsal. arXiv preprint arXiv:1911.11988, 2019.
@article{atkinson.etal:2019,
title={GRIm-RePR: Prioritising Generating Important Features for Pseudo-Rehearsal},
author={Craig Atkinson and
Brendan McCane and
Lech Szymanski and
Anthony Robins},
journal={arXiv preprint arXiv:1911.11988},
url={https://arxiv.org/abs/1911.11988},
year={2019}
}
Bibtex has been copied to clipboard.
C. Atkinson, B. McCane, L. Szymanski and A. Robins. Pseudo-recursal: Solving the catastrophic forgetting problem in deep neural networks. arXiv preprint arXiv:1802.03875, 2018.
@article{atkinson2018pseudo-recursal,
title={Pseudo-recursal: Solving the catastrophic forgetting problem in deep neural networks},
author={Atkinson, Craig and McCane, Brendan and Szymanski, Lech and Robins, Anthony},
journal={arXiv preprint arXiv:1802.03875},
url={https://arxiv.org/abs/1802.03875},
year={2018}
}
Bibtex has been copied to clipboard.