Tool

Reservoir computing on Mackey-Glass

Train a small echo-state network entirely in your browser to forecast the canonical chaotic benchmark series. Demonstrates chaos as a computational resource, not just a curiosity.

Reservoir size N: 150

Spectral radius ρ: 0.900

Leak rate α: 0.300

Echo state network on Mackey-Glass

state update:  s_{t+1} = (1 − α) s_t + α · tanh(W_in u_t + W s_t)
read-out:       ŷ_t = b + W_out · s_t   (ridge regression)
prediction:     run network closed-loop, feeding back ŷ_t as next input.

ρ near 1 puts the reservoir near the "edge of chaos" — good for nonlinear
time-series prediction. Standard ESN forecasts ~50 lookahead steps of MG
extremely well; further out, chaotic divergence saturates the error.

FAQ