Sciweavers

NIPS
2000
13 years 11 months ago
Position Variance, Recurrence and Perceptual Learning
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...
Zhaoping Li, Peter Dayan
NIPS
2000
13 years 11 months ago
Foundations for a Circuit Complexity Theory of Sensory Processing
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...
Robert A. Legenstein, Wolfgang Maass
NIPS
2000
13 years 11 months ago
Algorithms for Non-negative Matrix Factorization
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....
Daniel D. Lee, H. Sebastian Seung
NIPS
2000
13 years 11 months ago
Keeping Flexible Active Contours on Track using Metropolis Updates
Condensation, a form of likelihood-weighted particle filtering, has been successfully used to infer the shapes of highly constrained "active" contours in video sequences...
Trausti T. Kristjansson, Brendan J. Frey
NIPS
2000
13 years 11 months ago
Second Order Approximations for Probability Models
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...
Hilbert J. Kappen, Wim Wiegerinck
NIPS
2000
13 years 11 months ago
Hippocampally-Dependent Consolidation in a Hierarchical Model of Neocortex
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...
Szabolcs Káli, Peter Dayan
NIPS
2000
13 years 11 months ago
On Reversing Jensen's Inequality
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 ...
Tony Jebara, Alex Pentland
NIPS
2000
13 years 11 months ago
A Silicon Primitive for Competitive Learning
Competitive learning is a technique for training classification and clustering networks. We have designed and fabricated an 11transistor primitive, that we term an automaximizing ...
David Hsu, Miguel Figueroa, Chris Diorio