Cognitive Vision: Towards fully autonomous learning.

A framework for autonomous learning and participation in an audio-visual environment, such as table-top game playing, will be discussed.

A framework for autonomous learning and participation in an audio-visual environment will be presented. This is motivated by the aim of creating a synthetic agent that can observe a scene containing interactions between unknown objects and agents, and learn models of these sufficient to act in accordance with the implicit protocols present in the scene. Discrete concepts (utterances and object properties), and temporal protocols involving these concepts, are learned in an unsupervised manner from continuous sensor input alone.

Crucial to this learning process are methods for spatio-temporal attention applied to the audio and visual sensor data. These identify subsets of the sensor data relating to discrete concepts. Continuous methods are used to learn object property and utterance models from processed sensor data, forming a symbolic description. The PROGOL Inductive Logic Programming system is subsequently used to learn symbolic models of the temporal protocols presented in the presence of noise and over-representation in the symbolic data input to it. The models learned are used to drive a synthetic agent that can interact with the world in a semi-natural way. Our system has been evaluated in the domain of table-top game playing and has been shown to be successful at learning protocol behaviours in such real-world audio-visual environments.

Register to tell a friend about this lecture.

Comments

If you would like to comment about this lecture, please register here.

©2003-2006 Niminim Limited. Created by

Any ad revenue is entirely reinvested into the Lecture List's operating fund