XLSTM: Extended Long Short-Term Memory

Re:XLSTM: Extended Long Short-Term Memory by logicchains on Wednesday May 08, 2024 @06:54AM (#40296517)

To clarify, is the sLSTM strictly necessary (to achieve better accuracy than those other architectures), or is the mLSTM good enough? The [1/0] model in the paper seemed to do quite well.

[ Parent | on HN ]

Re:XLSTM: Extended Long Short-Term Memory by korbip on Wednesday May 08, 2024 @09:54AM (#40298149)

For language in general it seems fine. But there might be specific tasks where it is necessary indeed.

[ Parent | on HN ]