Cooperation Is All You Need

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Adeel, Ahsan, Muzaffar, Junaid, Zia, Fahad, Ahmed, Khubaib, Raza, Mohsin, Chaudary, Eamin, Riaz, Talha Bin, Saeed, Ahmed
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910913647345664
author Adeel, Ahsan
Muzaffar, Junaid
Zia, Fahad
Ahmed, Khubaib
Raza, Mohsin
Chaudary, Eamin
Riaz, Talha Bin
Saeed, Ahmed
author_facet Adeel, Ahsan
Muzaffar, Junaid
Zia, Fahad
Ahmed, Khubaib
Raza, Mohsin
Chaudary, Eamin
Riaz, Talha Bin
Saeed, Ahmed
contents Going beyond 'dendritic democracy', we introduce a 'democracy of local processors', termed Cooperator. Here we compare their capabilities when used in permutation invariant neural networks for reinforcement learning (RL), with machine learning algorithms based on Transformers, such as ChatGPT. Transformers are based on the long standing conception of integrate-and-fire 'point' neurons, whereas Cooperator is inspired by recent neurobiological breakthroughs suggesting that the cellular foundations of mental life depend on context-sensitive pyramidal neurons in the neocortex which have two functionally distinct points. Weshow that when used for RL, an algorithm based on Cooperator learns far quicker than that based on Transformer, even while having the same number of parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2305_10449
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Cooperation Is All You Need
Adeel, Ahsan
Muzaffar, Junaid
Zia, Fahad
Ahmed, Khubaib
Raza, Mohsin
Chaudary, Eamin
Riaz, Talha Bin
Saeed, Ahmed
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
Going beyond 'dendritic democracy', we introduce a 'democracy of local processors', termed Cooperator. Here we compare their capabilities when used in permutation invariant neural networks for reinforcement learning (RL), with machine learning algorithms based on Transformers, such as ChatGPT. Transformers are based on the long standing conception of integrate-and-fire 'point' neurons, whereas Cooperator is inspired by recent neurobiological breakthroughs suggesting that the cellular foundations of mental life depend on context-sensitive pyramidal neurons in the neocortex which have two functionally distinct points. Weshow that when used for RL, an algorithm based on Cooperator learns far quicker than that based on Transformer, even while having the same number of parameters.
title Cooperation Is All You Need
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2305.10449