Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

hidden state

A recurrent network's running summary of everything it has processed in a sequence so far.

Examples

  • A character-level RNN's hidden state after reading "th" already encodes that "e" is a likely next character.

See also

backpropagation through time LSTM encoder-decoder architecture
Read the full section →
Graph settings

Calculator