Inducing Functions through Reinforcement Learning without Task Specification

We report a bio-inspired framework for training a neural network through reinforcement learning to induce high level functions within the network. Based on the interpretation that animals have gained their cognitive functions such as object recognition - without ever being specifically trained for -...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Cho, Junmo, Dong-Hwan, Lee, Young-Gyu, Yoon
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 23.11.2021
Subjects
Decision making
Image classification
Learning
Neural networks
Object recognition
Training
Online AccessGet full text

Cover

More Information
Summary:We report a bio-inspired framework for training a neural network through reinforcement learning to induce high level functions within the network. Based on the interpretation that animals have gained their cognitive functions such as object recognition - without ever being specifically trained for - as a result of maximizing their fitness to the environment, we place our agent in an environment where developing certain functions may facilitate decision making. The experimental results show that high level functions, such as image classification and hidden variable estimation, can be naturally and simultaneously induced without any pre-training or specifying them.
ISSN:2331-8422