Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...
Graphical models have become the basic framework for topic based probabilistic modeling. Especially models with latent variables have proved to be effective in capturing hidden str...
Development of a wide spread project intended to teaching Computer Science, integrating a considerable number of students all over a country with big geographical extension and sc...
A key problem in video content analysis using dynamic graphical models is to learn a suitable model structure given some observed visual data. We propose a Completed Likelihood AI...
Spike synchronisation and de-synchronisation are important for feature binding and separation at various levels in the visual system. We present a model of complex valued neuron ac...