On the mapping between Hopfield networks and Restricted Boltzmann Machines

Authors: Matthew Smart, Anton Zilman

ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental we conduct experiments on the MNIST dataset which suggest the mapping provides a useful initialization to the RBM weights. and 3 EXPERIMENTS ON MNIST DATASET
Researcher Affiliation Academia Matthew Smart Department of Physics University of Toronto msmart@physics.utoronto.ca Anton Zilman Department of Physics and Institute for Biomedical Engingeering University of Toronto zilmana@physics.utoronto.ca
Pseudocode No The paper does not contain any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No No explicit statement about releasing code or links to a source code repository for the described methodology were found.
Open Datasets Yes We consider the popular MNIST dataset of handwritten digits (Le Cun et al., 1998)
Dataset Splits No The paper mentions training and testing images but does not explicitly provide details about a validation dataset split.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions 'scikit-learn (Pedregosa et al., 2011)' but does not provide specific version numbers for it or any other software dependencies.
Experiment Setup Yes In our experiments we train for 50 epochs with mini-batches of size 100 (3 105 weight updates) (...) The learning rate is η0 = 10 4 except the first 25 epochs of the randomly initialized weights in (b), where we used η = 5η0 due to slow training. (...) Training parameters: β = 2, and CD-20.