hochreiter-vanishing-gradient-1991-lstm-1995

OUT premise — entries/2026/06/21/wiki-Deep_learning-chunk-2.md

Created 2026-06-21T09:55:50+00:00

Hochreiter identified the vanishing gradient problem in his 1991 thesis, then co-invented LSTM (1995) to solve it; the modern LSTM with forget gate came in 1999