Expressive probabilistic sampling in recurrent neural networks

Authors: Shirui Chen, Linxing Jiang, Rajesh PN Rao, Eric Shea-Brown

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 4 Experimental results
Researcher Affiliation Academia Shirui Chen Department of Applied Mathematics University of Washington, Seattle sc256@uw.edu Linxing Preston Jiang Paul G. Allen School of Computer Science & Engineering University of Washington, Seattle prestonj@cs.washington.edu Rajesh P. N. Rao Paul G. Allen School of Computer Science & Engineering and Center for Neurotechnology University of Washington, Seattle rao@cs.washington.edu Eric Shea-Brown Department of Applied Mathematics Computational Neuroscience Center University of Washington, Seattle etsb@uw.edu
Pseudocode Yes Algorithm 1: Training RSN
Open Source Code Yes All code is available on Github
Open Datasets Yes MNIST dataset [32]
Dataset Splits No The paper mentions using MNIST and CIFAR-10 datasets and training for a certain number of iterations/epochs, but does not explicitly provide the train/validation/test dataset splits with percentages or sample counts.
Hardware Specification Yes All experiments were run on one NVIDIA Quadro RTX 6000 GPU.
Software Dependencies No The paper mentions using the Adam optimizer but does not provide specific version numbers for software dependencies or libraries used in the experiments.
Experiment Setup Yes The learning rate was 0.0001, and the batch size was 128.