Sciweavers

NIPS
2000
13 years 11 months ago
Periodic Component Analysis: An Eigenvalue Method for Representing Periodic Structure in Speech
An eigenvalue method is developed for analyzing periodic structure in speech. Signals are analyzed by a matrix diagonalization reminiscent of methods for principal component analy...
Lawrence K. Saul, Jont B. Allen
NIPS
2000
13 years 11 months ago
Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task
The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product o...
Brian Sallans, Geoffrey E. Hinton
NIPS
2000
13 years 11 months ago
Occam's Razor
The Bayesian paradigm apparently only sometimes gives rise to Occam's Razor; at other times very large models perform well. We give simple examples of both kinds of behaviour...
Carl Edward Rasmussen, Zoubin Ghahramani
NIPS
2000
13 years 11 months ago
The Use of Classifiers in Sequential Inference
We study the problem of combining the outcomes of several different classifiers in a way that provides a coherent inference that satisfies some constraints. In particular, we deve...
Vasin Punyakanok, Dan Roth
NIPS
2000
13 years 11 months ago
Bayes Networks on Ice: Robotic Search for Antarctic Meteorites
A Bayes network based classifier for distinguishing terrestrial rocks from meteorites is implemented onboard the Nomad robot. Equipped with a camera, spectrometer and eddy current...
Liam Pedersen, Dimitrios Apostolopoulos, William W...
NIPS
2000
13 years 11 months ago
Learning Switching Linear Models of Human Motion
The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. Effective models of human dynamics can be learned from motion capture data usi...
Vladimir Pavlovic, James M. Rehg, John MacCormick
NIPS
2000
13 years 11 months ago
Learning and Tracking Cyclic Human Motion
We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segm...
Dirk Ormoneit, Hedvig Sidenbladh, Michael J. Black...
NIPS
2000
13 years 11 months ago
Interactive Parts Model: An Application to Recognition of On-line Cursive Script
In this work, we introduce an Interactive Parts (IP) model as an alternative to Hidden Markov Models (HMMs). We tested both models on a database of on-line cursive script. We show...
Predrag Neskovic, Philip C. Davis, Leon N. Cooper
NIPS
2000
13 years 11 months ago
Learning Continuous Distributions: Simulations With Field Theoretic Priors
Learning of a smooth but nonparametric probability density can be regularized using methods of Quantum Field Theory. We implement a field theoretic prior numerically, test its eff...
Ilya Nemenman, William Bialek
NIPS
2000
13 years 11 months ago
Active Inference in Concept Learning
Jonathan D. Nelson, Javier R. Movellan