What does LSTM mean?

LSTM stands for Long Short-Term Memory, a recurrent neural network built to learn long-range dependencies in sequences. Sepp Hochreiter and Jürgen Schmidhuber introduced it in a 1997 Neural Computation paper of the same name. The name refers to making short-term memory, held in the network's activations rather than its weights, last for a long time.

Plain RNNs struggle with long gaps because gradients shrink or explode over many time steps. An LSTM adds an additively updated cell state, cₜ = fₜ ⊙ cₜ₋₁ + iₜ ⊙ c̃ₜ, with output hₜ = oₜ ⊙ tanh(cₜ). The forget, input and output gates are sigmoid layers that decide what to erase, write and expose. The forget gate came later, added by Gers, Schmidhuber and Cummins in 1999.

Common follow-ups: how an LSTM differs from a GRU, which has two gates and no separate cell state, and why Transformers, which process a whole sequence in parallel, replaced it in most NLP after 2017. LSTMs remain common for time series and on-device models.