On the Challenges of Physical Implementations of RBMs

Authors: Vincent Dumoulin, Ian Goodfellow, Aaron Courville, Yoshua Bengio

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct software simulations to determine how harmful each of these restrictions is. Our simulations are based on the D-Wave Two computer, but the issues we investigate arise in most forms of physical computation. We used standard train / test split for both the MNIST (Le Cun et al. 1998) and Connect-4 and OCR Letters (Larochelle, Bengio, and Turian 2010) datasets.
Researcher Affiliation Academia Vincent Dumoulin and Ian J. Goodfellow and Aaron Courville and Yoshua Bengio D epartement d informatique et de recherche op erationnelle Universit e de Montr eeal Montr eal, QC H3C 3J7 {dumouliv,goodfeli,courvila}@iro.umontreal.ca yoshua.bengio@umontreal.ca
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements or links indicating that source code for the methodology is openly available.
Open Datasets Yes We used standard train / test split for both the MNIST (Le Cun et al. 1998) and Connect-4 and OCR Letters (Larochelle, Bengio, and Turian 2010) datasets.
Dataset Splits Yes We used standard train / test split for both the MNIST (Le Cun et al. 1998) and Connect-4 and OCR Letters (Larochelle, Bengio, and Turian 2010) datasets.
Hardware Specification No The paper mentions running simulations 'on a GPU' but does not provide specific details such as GPU model, CPU type, or memory, which are necessary for hardware specification.
Software Dependencies No The paper mentions 'PCD-15' as a training method but does not list specific software libraries or tools with version numbers (e.g., 'PyTorch 1.9', 'Python 3.8') that would be needed for replication.
Experiment Setup Yes All models were trained using PCD-15. Training examples were binarized every time they were presented by sampling from a Bernoulli distribution, such that the grayscale value in [0, 1] in the original image gives the probability of that pixel being a 1 in the binary image. Unless explicitly stated, all models were trained using the same hyperparameters.