Text full multimedia monochrome

First time here?

Find out more about how The Lecture List works.

Coronavirus situation update

Our lecture organisers may or may not have had time to update their events with cancellation notices. Clearly social gatherings are to be avoided and that includes lectures. STAY AT HOME FOLKS, PLEASE.


Find out what you can do to keep The Lecture List online

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.


Dr Derek Magee | talks | www


Date and Time:

9 March 2005 at 1:30 pm


1 hour



School of Maths, Kingston University
School of Maths, Kingston University
Penrhyn Road
Kingston upon Thames
+44 20 8547 7922

More at School of Maths, Kingston University...




Available from:

Additional Information:

Research seminars are usually held in the Penrhyn Road building of Kingston University. Check the web site for full details and room information.

Register to tell a friend about this lecture.


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


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