Formalizing locality for normative synaptic plasticity models

Authors: Colin Bredenberg, Ezekiel Williams, Cristina Savin, Blake Richards, Guillaume Lajoie

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Here, we address this lack of clarity by proposing formal and operational definitions of locality. Specifically, we define different classes of locality, each of which makes clear what quantities cannot be included in a learning rule if an algorithm is to qualify as local with respect to a given (biological) constraint. We subsequently use this framework to distill testable predictions from various classes of biologically plausible synaptic plasticity models that are robust to arbitrary choices about neural network architecture. Therefore, our framework can be used to guide claims of biological plausibility and to identify potential means of experimentally falsifying a proposed learning algorithm for the brain.
Researcher Affiliation Academia Colin Bredenberg Mila Quebec AI Institute Montreal, Quebec H2S 3H1 Ezekiel Williams Mila Quebec AI Institute Montreal, Quebec H2S 3H1 Cristina Savin New York University New York, NY 10003 Blake Richards Mc Gill University Mila Quebec AI Institute Montreal, Quebec H2S 3H1 Guillaume Lajoie Université de Montréal Mila Quebec AI Institute Montreal, Quebec H2S 3H1
Pseudocode No The paper describes algorithms and their properties but does not include any formal pseudocode blocks or algorithms.
Open Source Code No The paper does not mention or provide any links to open-source code related to the formal framework or analysis described in the paper.
Open Datasets No The paper is theoretical and does not use or analyze any datasets.
Dataset Splits No The paper is theoretical and does not perform experiments with dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not involve computational experiments, so no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and focuses on formalizing concepts; it does not mention specific software dependencies or their version numbers required for reproducibility.
Experiment Setup No The paper is theoretical and does not involve experimental setups, hyperparameters, or training configurations.