Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/164368
Title: Representation learning in the artificial and biological neural networks underlying sensorimotor integration
Authors: Suhaimi, Ahmad
Lim, Amos W. H.
Chia, Xin Wei
Li, Chunyue
Makino, Hiroshi
Keywords: Science::Medicine
Issue Date: 2022
Source: Suhaimi, A., Lim, A. W. H., Chia, X. W., Li, C. & Makino, H. (2022). Representation learning in the artificial and biological neural networks underlying sensorimotor integration. Science Advances, 8(22), eabn0984-. https://dx.doi.org/10.1126/sciadv.abn0984
Project: 2018-T1-001-032
RT11/19
MOE2018-T2-1-021
MOE2017-T3-1-002
Journal: Science Advances
Abstract: The integration of deep learning and theories of reinforcement learning (RL) is a promising avenue to explore novel hypotheses on reward-based learning and decision-making in humans and other animals. Here, we trained deep RL agents and mice in the same sensorimotor task with high-dimensional state and action space and studied representation learning in their respective neural networks. Evaluation of thousands of neural network models with extensive hyperparameter search revealed that learning-dependent enrichment of state-value and policy representations of the task-performance-optimized deep RL agent closely resembled neural activity of the posterior parietal cortex (PPC). These representations were critical for the task performance in both systems. PPC neurons also exhibited representations of the internally defined subgoal, a feature of deep RL algorithms postulated to improve sample efficiency. Such striking resemblance between the artificial and biological networks and their functional convergence in sensorimotor integration offers new opportunities to better understand respective intelligent systems.
URI: https://hdl.handle.net/10356/164368
ISSN: 2375-2548
DOI: 10.1126/sciadv.abn0984
Rights: © 2022 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:LKCMedicine Journal Articles

Files in This Item:
File Description SizeFormat 
sciadv.abn0984.pdf6.81 MBAdobe PDFView/Open

SCOPUSTM   
Citations 50

2
Updated on Feb 2, 2023

Page view(s)

14
Updated on Feb 6, 2023

Download(s)

6
Updated on Feb 6, 2023

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.