Stimulus arrays are inevitably presented at different positions on the retina in visual tasks, even those that nominally require fixation. In particular, this applies to many perc...
We introduce total wire length as salient complexity measure for an analysis of the circuit complexity of sensory processing in biological neural systems and neuromorphic engineer...
Non-negative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. Two different multiplicative algorithms for NMF are analyzed....
Condensation, a form of likelihood-weighted particle filtering, has been successfully used to infer the shapes of highly constrained "active" contours in video sequences...
In this paper, we derive a second order mean field theory for directed graphical probability models. By using an information theoretic argument it is shown how this can be done in...
In memory consolidation, declarative memories which initially require the hippocampus for their recall, ultimately become independent of it. Consolidation has been the focus of nu...
Jensen's inequality is a powerful mathematical tool and one of the workhorses in statistical learning. Its applications therein include the EM algorithm, Bayesian estimation ...
Competitive learning is a technique for training classification and clustering networks. We have designed and fabricated an 11transistor primitive, that we term an automaximizing ...