We introduce into the classical Perceptron algorithm with margin a mechanism of unlearning which in the course of the regular update allows for a reduction of possible contributio...
Abstract. Mainstream surrogate approaches for multi-objective problems build one approximation for each objective. Mono-surrogate approaches instead aim at characterizing the Paret...
In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...
A novel approach for event summarization and rare event detection is proposed. Unlike conventional methods that deal with event summarization and rare event detection independently...
Abstract. We present a novel technique where a medical image segmentation system is evolved using genetic programming. The evolved system was trained on just 8 images outlined by a...