Neural-symbolic systems are hybrid systems that integrate symbolic logic and neural networks. The goal of neural-symbolic integration is to benefit from the combination of feature...
This paper develops a model for precisely defining how an agent interacts with objects in its environment through the use of its capabilities. Capabilities are recursively defined ...
This paper presents a new method for segmentation of images into large regions that reflect the real world objects present in a scene. It explores the feasibility of utilizing sp...
We present new fingerprint classification algorithms based on two machine learning approaches: support vector machines (SVMs), and recursive neural networks (RNNs). RNNs are traine...
Yuan Yao, Gian Luca Marcialis, Massimiliano Pontil...
Abstract In this paper we present a new rule-based approach for consistency preserving view updating in deductive databases. Based on rule transformations performed during schema d...