Adaptation Accelerating Sampling-based Bayesian Inference in Attractor Neural Networks

Authors: Xingsi Dong, Zilong Ji, Tianhao Chu, Tiejun Huang, Wenhao Zhang, Si Wu

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Simulation results validate our theoretical analyses.
Researcher Affiliation Academia 1, School of Psychology and Cognitive Sciences, IDG/Mc Govern Institute for Brain Research, PKU-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Center of Quantitative Biology, Peking University. 2. Lyda Hill Department of Bioinformatics, O Donnell Brain Institute, UT Southwestern Medical Center. 3. Institute of Cognitive Neuroscience, University College London 4. School of Computer Science, Peking University.
Pseudocode No The paper provides mathematical equations and descriptions of dynamics but does not include structured pseudocode or algorithm blocks.
Open Source Code Yes We have included the code for reproducing the main results in SI.
Open Datasets No The paper uses a 'linear Gaussian generative model' as a theoretical framework for its simulations rather than an external, publicly available dataset. It defines observations and latent features internally.
Dataset Splits No Since the paper does not use an external dataset, it does not specify train/validation/test splits. The analysis focuses on the convergence of sampled distributions within its theoretical model.
Hardware Specification No We do not use GPU or CPU clusters, and it is sufficient to run our code on a laptop.
Software Dependencies No The paper does not provide specific names or version numbers for ancillary software components, libraries, or solvers used in the experiments.
Experiment Setup Yes For the setting of hyperparameters, see SI.1.