This paper looks at the problem of data prioritization, commonly found in mobile ad-hoc networks. The proposed general solution uses a machine learning approach in order to learn ...
This paper presents a new architecture of neural networks designed for pattern recognition. The concept of induction graphs coupled with a divide-and-conquer strategy defines a Gr...
We propose a framework for quantitative security analysis of machine learning methods. Key issus of this framework are a formal specification of the deployed learning model and a...
Ideally pattern recognition machines provide constant output when the inputs are transformed under a group G of desired invariances. These invariances can be achieved by enhancing...
0 Temporal Abstractions and Case-Based Reasoning for Medical Course Data: Two Prognostic Applications R. Schmidt and R. Gierl University of Rostock, Germany 9.00-9.30 Local Learnin...