[StackRnn] - add recurrent RBM stack with character-level LM notebook

Browse Source

Implements StackRnn: a cascaded/recurrent RBM where the visible layer at
each time step is the concatenation of the previous hidden state (context)
and the current sensory input — V[t] = [context | x_t].  Weights are
shared across time steps (RTRBM-style concatenation variant).

- stack_rnn.py: StackRnn with step(), reconstruct(), reset(), train(),
  make_layer() factory; supports greedy layer-wise training over sequences
  of shape (num_seq, T, sensory_size)
- test_rnn.py: single-layer, two-layer, and save/load tests
- moby_rnn.ipynb: character-level language model on Moby Dick; one-hot
  encoding, clamped-Gibbs next-char prediction, free text generation,
  hidden-state trace and character-distribution visualisations

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

...

This commit is contained in:

jens

2026-05-31 11:27:07 +02:00

co-authored by Claude Sonnet 4.6

parent 17429ddce8

commit eb1f96f4ec

3 changed files with 884 additions and 2 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

moby_rnn.ipynb

+591

File diff suppressed because one or more lines are too long