Distinguishing Learning Rules with Brain Machine Interfaces

Authors: Jacob Portes, Christian Schmid, James M Murray

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

Reproducibility Variable Result LLM Response
Research Type Experimental We model a cursor-control BMI task using recurrent neural networks, showing that learning rules can be distinguished in simulated experiments using only observations that a neuroscience experimenter would plausibly have access to. All simulations were run on a CPU
Researcher Affiliation Academia Jacob P. Portes Center for Theoretical Neuroscience Columbia University j.portes@columbia.edu; Christian Schmid Institute of Neuroscience University of Oregon cschmid9@uoregon.edu; James M. Murray Institute of Neuroscience University of Oregon jmurray9@uoregon.edu
Pseudocode No The paper describes learning rules with equations but does not provide pseudocode or a clearly labeled algorithm block.
Open Source Code Yes Code included as supplementary material
Open Datasets No The paper describes simulating and training RNNs for a cursor-control task. It does not use a pre-existing, publicly available dataset with concrete access information; the data is generated through simulation.
Dataset Splits No The paper describes pretraining and then observing activity during early and late phases of learning. It does not mention explicit training/validation/test dataset splits with percentages or sample counts.
Hardware Specification No All simulations were run on a CPU
Software Dependencies No The paper does not list specific software dependencies with version numbers.
Experiment Setup No The paper describes the general setup for simulations (e.g., pretraining, changing decoder, training with SL/RL) but does not provide specific hyperparameters like learning rates, batch sizes, or optimizer settings in the main text.