This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Vagrant Gautam
dippedrusk.com
did:plc:5oqzqcvlkuds33ql6mnpdjlv
#AdventOfPapers 2: Were RNNs all we needed? (rec from @vn-ml.bsky.social) This is partly a history of machine learning for sequences (tl;dr RNNs had vanishing+exploding gradients, then LSTMs and GRUs couldn't scale to long contexts or train fast, then we got transformers)
arxiv.org/abs/2410.01201
https://arxiv.org/abs/2410.01201
2024-12-04T17:18:44.851Z