When Do Differences Matter? On-Line Feature Extraction Through Cognitive Economy

04/15/2004
by   David J. Finton, et al.
0

For an intelligent agent to be truly autonomous, it must be able to adapt its representation to the requirements of its task as it interacts with the world. Most current approaches to on-line feature extraction are ad hoc; in contrast, this paper presents an algorithm that bases judgments of state compatibility and state-space abstraction on principled criteria derived from the psychological principle of cognitive economy. The algorithm incorporates an active form of Q-learning, and partitions continuous state-spaces by merging and splitting Voronoi regions. The experiments illustrate a new methodology for testing and comparing representations by means of learning curves. Results from the puck-on-a-hill task demonstrate the algorithm's ability to learn effective representations, superior to those produced by some other, well-known, methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/02/2017

A global feature extraction model for the effective computer aided diagnosis of mild cognitive impairment using structural MRI images

Multiple modalities of biomarkers have been proved to be very sensitive ...
research
10/26/2020

Automatic Feature Extraction for Classifying Audio Data

Today, many private households as well as broadcasting or film companies...
research
11/15/2016

Feature Extraction and Soft Computing Methods for Aerospace Structure Defect Classification

This study concerns the effectiveness of several techniques and methods ...
research
09/15/2020

Autonomous Learning of Features for Control: Experiments with Embodied and Situated Agents

As discussed in previous studies, the efficacy of evolutionary or reinfo...
research
05/03/2022

Extending the View Composition Algebra to Hierarchical Data

Comparison is a core task in visual analysis. Although there are numerou...

Please sign up or login with your details

Forgot password? Click here to reset