We present and analyze a novel regularization technique based on enhancing our dataset with corrupted copies of our original data. The motivation is that since the learning algori...
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, ...
It is well known that prior knowledge or bias can speed up learning, at least in theory. It has proved di cult to make constructive use of prior knowledge, so that approximately c...
This paper presents a novel framework called proto-reinforcement learning (PRL), based on a mathematical model of a proto-value function: these are task-independent basis function...
We consider the problem of learning a similarity function from a set of positive equivalence constraints, i.e. 'similar' point pairs. We define the similarity in informa...