jensandClaude Sonnet 4.6 7d48f835a6 [bugfix] - fix momentum reset, cd_gaussian_gaussian noise, rms_error, label CuPy compat
- train.py: grad_zero() was called inside the epoch loop, resetting momentum
  to zero before every update — momentum had no effect in the default full-batch
  case. Moved outside the loop so momentum accumulates across epochs.
- train.py: cd_gaussian_gaussian: use mean h for weight updates and sampled h
  to drive the negative visible reconstruction (same pattern as cd_gaussian_binary fix).
  Remove spurious Gaussian noise added to data_neg before computing h_probs_neg.
- matrix.py: rms_error divided by d_err_squared[1] (row 1) instead of
  d_err_squared.shape[1] (column count).
- label.py: _dec_binary used reversed() on a CuPy array — replaced with np.flip().
  label2vec_onehot now returns np.stack() array instead of a Python list.
  vec2label_onehot implemented via np.argmax (was returning None).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-30 14:46:45 +02:00
2025-12-19 11:11:00 +01:00
2026-01-11 11:23:35 +01:00
2026-01-10 21:44:03 +01:00
2025-12-19 15:20:04 +01:00
2026-01-11 11:23:35 +01:00
2026-01-10 19:58:39 +01:00
2025-12-18 07:56:45 +01:00
2026-01-06 18:00:26 +01:00
2025-12-16 21:46:00 +01:00
S
Description
Restricted Boltzmann Machine (RBM) for python
Readme
65 MiB
Languages
Jupyter Notebook 96.9%
Python 3.1%