Neuromodulated Goal-Driven Perception in Uncertain Domains

In uncertain domains, the goals are often unknown and need to be predicted by the organism or system. In this paper, contrastive excitation backprop (c-EB) was used in a goal-driven perception task with pairs of noisy MNIST digits, where the system had to increase attention to one of the two digits...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-02
Main Authors: Zou, Xinyun, Kolouri, Soheil, Pilly, Praveen K, Krichmar, Jeffrey L
Format: Article
Language:English
Subjects:
Background noise
Digits
Distance learning
Domains
Mathematical models
Perception
Uncertainty
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In uncertain domains, the goals are often unknown and need to be predicted by the organism or system. In this paper, contrastive excitation backprop (c-EB) was used in a goal-driven perception task with pairs of noisy MNIST digits, where the system had to increase attention to one of the two digits corresponding to a goal (i.e., even, odd, low value, or high value) and decrease attention to the distractor digit or noisy background pixels. Because the valid goal was unknown, an online learning model based on the cholinergic and noradrenergic neuromodulatory systems was used to predict a noisy goal (expected uncertainty) and re-adapt when the goal changed (unexpected uncertainty). This neurobiologically plausible model demonstrates how neuromodulatory systems can predict goals in uncertain domains and how attentional mechanisms can enhance the perception of that goal.
ISSN:2331-8422