|
NeuroCOLT |
Neural Networks and Computational Learning Theory |
|
|
The areas of research of the NeuroCOLT project are: Foundations and Algorithmics of LearningTo develop novel models and techniques for analysing learning systems. In particular, models that more accurately reflect real world conditions, and algorithms which perform well in the developed models. Specification and Prototyping of Novel Learning SystemsTo translate novel insights into specifications for practical learning systems which take advantage of the fundamental understanding achieved and hence either have improved performance or more efficient learning algorithms. Real Valued Complexity and Function ClassesTo assess the computational richness of function classes and their suitability for use in learning systems.
|