Energy-based learning, visible

Train a full Boltzmann machine or an RBM and inspect stochastic states, weights, energy, and reconstruction error.

positive weight negative weight

Model Visible Hidden Learning rate Temperature CD / Gibbs steps Steps / second8

Ready. Adjust the dataset or start training.

Epoch 0Error 0.0000Energy 0.0000Weight RMS 0.0000

Network state

idle

Inference and learned distribution

Inference pauses training and reads the current weights without updating them.

weights frozen

States evaluated / observed0Entropy (nats)0.000Probability sum0.000000

Hidden posterior P(H | input)

No inference result.

Visible reconstruction

No inference result.

Most likely visible states

normalized probability

No learned distribution yet.

Learning functions

These functions execute in this tab. Invalid code is rejected without replacing the active functions.

Activation probability Weight update

Original functions active.

Reading the experiment

RBM: positive associations come from data and hidden probabilities; negative associations come from a CD-k reconstruction.

Full BM: the positive phase clamps visible data while the negative phase lets every unit run freely. More Gibbs steps generally reduce sampling bias but cost more time.

Temperature: lower values make states more deterministic. Edge width shows magnitude; green and red show weight sign.

Model behavior follows Ackley, Hinton, and Sejnowski (1985), with RBM contrastive-divergence controls based on Hinton's practical guide. Source links are in the README.