Click a stage.
Figures stated in the episode.
Stored pattern (+,+,−,+). Click a neuron to corrupt it, then update.
E = −Σi<j wij sisj for this single-pattern network.
Exact arithmetic on small example sets (n=4).
W pj = (n−m) pj + cross-talk.
The paper writes out the disturbance term but states no stability theorem for non-orthogonal patterns.
P(unit on) = σ(ΔE / T). As T→0 it becomes the Hopfield step rule (Lemma 4.4).
Bars: exact Boltzmann π. Dots: random-scan Gibbs counts.
Hover a cell. Diagonal is strictly positive (aperiodic); single bit flips connect all states.
T = [[2,1],[1,3]], x = (t, 1−t). f(x) = mini (Tx)i/xi; its maximum is the Perron root.