We define the concept of dependence among multiple variables using maximum entropy techniques and introduce a graphical notation to denote the dependencies. Direct inference of in...
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...
Visualisation Systems are in general designed to maximise the cognitive ability of system users particularly when exposed to large sets of otherwise difficult to comprehend data, ...
—This paper considers the problem of temporally fusing classifier outputs to improve the overall diagnostic classification accuracy in safety-critical systems. Here, we discuss d...
Statistical measures coming from information theory represent interesting bases for image and video processing tasks such as image retrieval and video object tracking. For example...