AI / ML VisualizerRuns in your browser · No API keyOpen Model
← All topics

Sequence Models

Encoder–Decoder

Pass an encoder context into a small recurrent decoder.

SEQ2SEQ · unrolled through timeSEQ2SEQ · unrolled through timex1 = 1t=1h=0.664→x2 = 0t=2h=0.3203→x3 = -1t=3h=-0.5648→x4 = 0.5t=4h=0.1171→x5 = 0t=5h=0.0585Shared weights · h(t−1) → cell → h(t)
Step 0 / 4
hₜ = tanh(Wx × xₜ + Wh × hₜ₋₁ + b)
tanh(0.8×1 + 0.5×0 + 0)
Hidden state = 0.664
Memory over timeMemory over time0-21-1203142Hidden

Encoder context → decoder

The final encoder hidden state initializes this scalar decoder. Toy numeric sequence, not a trained translator.

Decoder hidden states (zero input) · 1 × 3

Continue exploring

Vanilla RNN →Backpropagation Through Time →LSTM →

No account required. Local images and model files stay in your browser. Educational models demonstrate mechanisms; they are not production predictors.