Sciweavers

NIPS
1998
13 years 11 months ago
Risk Sensitive Reinforcement Learning
In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with re...
Ralph Neuneier, Oliver Mihatsch
NIPS
1998
13 years 11 months ago
Controlling the Complexity of HMM Systems by Regularization
This paper introduces a method for regularization of HMM systems that avoids parameter overfitting caused by insufficient training data. Regularization is done by augmenting the E...
Christoph Neukirchen, Gerhard Rigoll
NIPS
1998
13 years 11 months ago
Scheduling Straight-Line Code Using Reinforcement Learning and Rollouts
The execution order of a block of computer instructions can make a difference in its running time by a factor of two or more. In order to achieve the best possible speed, compiler...
Amy McGovern, J. Eliot B. Moss
NIPS
1998
13 years 11 months ago
Bayesian Modeling of Facial Similarity
In previous work 6, 9, 10], we advanced a new technique for direct visual matching of images for the purposes of face recognition and image retrieval, using a probabilistic measur...
Baback Moghaddam, Tony Jebara, Alex Pentland
NIPS
1998
13 years 11 months ago
Computational Differences between Asymmetrical and Symmetrical Networks
Symmetrically connected recurrent networks have recently been used as models of a host of neural computations. However, biological neural networks have asymmetrical connections, at...
Zhaoping Li, Peter Dayan
NIPS
1998
13 years 11 months ago
Coding Time-Varying Signals Using Sparse, Shift-Invariant Representations
A common way to represent a time series is to divide it into shortduration blocks, each of which is then represented by a set of basis functions. A limitation of this approach, ho...
Michael S. Lewicki, Terrence J. Sejnowski
NIPS
1998
13 years 11 months ago
Learning a Continuous Hidden Variable Model for Binary Data
A directed generative model for binary data using a small number of hidden continuous units is investigated. A clipping nonlinearity distinguishes the model from conventional prin...
Daniel D. Lee, Haim Sompolinsky
NIPS
1998
13 years 11 months ago
A Polygonal Line Algorithm for Constructing Principal Curves
Principal curves have been defined as "self consistent" smooth curves which pass through the "middle" of a d-dimensional probability distribution or data cloud...
Balázs Kégl, Adam Krzyzak, Tam&aacut...