Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference
Paper summary Catastrophic forgetting is the tendency of an neural network to forget previously learned information when learning new information. This paper combats that by keeping a buffer of experience and applying meta-learning to it. They call their new module Meta Experience Replay or MER. How does this work? At each update they compute multiple possible updates to the model weights. One for the new batch of information and some more updates for batches of previous experience. Then they apply meta-learning using the REPTILE algorithm, here the meta-model sees each possible update and has to predict the output which combines them with the least interference. This is done by predicting an update vector that maximizes the dot product between the new and old update vectors, that way it transfers as much learning as possible from the new update without interfering with the old updates. https://i.imgur.com/TG4mZOn.png Does it work? Yes, while it may take longer to train, the results show that it generalizes better and needs a much smaller buffer of experience than the popular approach of using replay buffers.
arxiv.org
arxiv-sanity.com
scholar.google.com
Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference
Matthew Riemer and Ignacio Cases and Robert Ajemian and Miao Liu and Irina Rish and Yuhai Tu and Gerald Tesauro
arXiv e-Print archive - 2018 via Local arXiv
Keywords: cs.LG, cs.AI, stat.ML

more

Summary by wassname 2 weeks ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and