lstm-hochreiter-schmidhuber-1997-standard-reference

IN premisesummaries/2026/08/24/wiki-Transformer_deep_learning_architecture-chunk-6-chunk-1.md

Created 2026-08-24T17:11:27+00:00

The standard LSTM reference is Hochreiter & Schmidhuber, 1997, published in Neural Computation 9(8):1735-1780 (doi:10.1162/neco.1997.9.8.1735).

Summary

This pins down the one authoritative paper to cite when talking about where the LSTM architecture comes from, so the system has a single agreed-upon source rather than letting references drift to later surveys or alternative attributions. It matters because any downstream claim about how LSTMs work, when they were introduced, or who is credited with the design traces back to this 1997 Neural Computation article as the fixed point.