CEHCApr 25, 2014

CATOS: Computer Aided Training/Observing System

arXiv:1404.6384v1
Originality Synthesis-oriented
AI Analysis

This addresses the problem of human interference and bias in animal training and observation for behavioral biology, though it is incremental as it builds on existing automation concepts.

The study tackled the need for autonomous systems in animal behavioral biology by developing CATOS, a computer-aided training/observing system, and tested it in a pilot experiment where cats were trained to press buttons in response to sounds, achieving over 70% correctness for one cat.

In animal behavioral biology, there are several cases in which an autonomous observing/training system would be useful. 1) Observation of certain species continuously, or for documenting specific events, which happen irregularly; 2) Longterm intensive training of animals in preparation for behavioral experiments; and 3) Training and testing of animals without human interference, to eliminate potential cues and biases induced by humans. The primary goal of this study is to build a system named CATOS (Computer Aided Training/Observing System) that could be used in the above situations. As a proof of concept, the system was built and tested in a pilot experiment, in which cats were trained to press three buttons differently in response to three different sounds (human speech) to receive food rewards. The system was built in use for about 6 months, successfully training two cats. One cat learned to press a particular button, out of three buttons, to obtain the food reward with over 70 percent correctness.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes