Support Constraints Machines
published: Oct. 17, 2011, recorded: September 2011, views: 3612
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
The theory of kernel machines has had an enormous impact in different in different fields, including pattern recognition and computer vision. However, it offers quite primitive models of most interesting problems, especially when the emergence of intelligence arises from the joint presence of supervised examples and knowledge granules. I this talk, I discuss an in-depth reformulation of the theory that is based on the abstract notion of constraint. I give a picture of the “agent body” in terms of representation theorems by extending the classic framework of kernel machines in such a way to incorporate logic formalisms, like first-order logic. This is made possible by the unification of continuous and discrete computational mechanisms in the same functional framework, so as any stimulus, like supervised examples and logic predicates, is translated into a constraint. The learning, which is based on constrained variational calculus, is either guided by a parsimonious match of the constraints or by unsupervised mechanisms expressed in terms of the minimization of the entropy. I show some experiments with different kinds of symbolic and sub-symbolic constraints, and then I give insights on the adoption of the proposed framework in computer vision. It is shown that in most interesting tasks the learning from constraints naturally leads to “deep architectures”, that emerge when following the developmental principle of focusing attention on "easy constraints", at each stage. Interestingly, this suggests that stage-based learning, as discussed in developmental psychology, might not be primarily the outcome of biology, but it could be instead the consequence of optimization principles and complexity issues that hold regardless of the "body".
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !