Sciweavers

NIPS
2004
13 years 11 months ago
Learning Hyper-Features for Visual Identification
We address the problem of identifying specific instances of a class (cars) from a set of images all belonging to that class. Although we cannot build a model for any particular in...
Andras Ferencz, Erik G. Learned-Miller, Jitendra M...
NIPS
2004
13 years 11 months ago
A Cost-Shaping LP for Bellman Error Minimization with Performance Guarantees
We introduce a new algorithm based on linear programming that approximates the differential value function of an average-cost Markov decision process via a linear combination of p...
Daniela Pucci de Farias, Benjamin Van Roy
NIPS
2004
13 years 11 months ago
Exploration-Exploitation Tradeoffs for Experts Algorithms in Reactive Environments
A reactive environment is one that responds to the actions of an agent rather than evolving obliviously. In reactive environments, experts algorithms must balance exploration and ...
Daniela Pucci de Farias, Nimrod Megiddo
NIPS
2004
13 years 11 months ago
Experts in a Markov Decision Process
We consider an MDP setting in which the reward function is allowed to change during each time step of play (possibly in an adversarial manner), yet the dynamics remain fixed. Simi...
Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
NIPS
2004
13 years 11 months ago
Seeing through water
We consider the problem of recovering an underwater image distorted by surface waves. A large amount of video data of the distorted image is acquired. The problem is posed in term...
Alexei A. Efros, Volkan Isler, Jianbo Shi, Mirk&oa...
NIPS
2004
13 years 11 months ago
Sparse Coding of Natural Images Using an Overcomplete Set of Limited Capacity Units
It has been suggested that the primary goal of the sensory system is to represent input in such a way as to reduce the high degree of redundancy. Given a noisy neural representati...
Eizaburo Doi, Michael S. Lewicki
NIPS
2004
13 years 11 months ago
Pictorial Structures for Molecular Modeling: Interpreting Density Maps
X-ray crystallography is currently the most common way protein structures are elucidated. One of the most time-consuming steps in the crystallographic process is interpretation of...
Frank DiMaio, Jude W. Shavlik, George N. Phillips
NIPS
2004
13 years 11 months ago
Triangle Fixing Algorithms for the Metric Nearness Problem
Various problems in machine learning, databases, and statistics involve pairwise distances among a set of objects. It is often desirable for these distances to satisfy the propert...
Inderjit S. Dhillon, Suvrit Sra, Joel A. Tropp
NIPS
2004
13 years 11 months ago
Bayesian inference in spiking neurons
We propose a new interpretation of spiking neurons as Bayesian integrators accumulating evidence over time about events in the external world or the body, and communicating to oth...
Sophie Deneve
NIPS
2004
13 years 11 months ago
The Power of Selective Memory: Self-Bounded Learning of Prediction Suffix Trees
Prediction suffix trees (PST) provide a popular and effective tool for tasks such as compression, classification, and language modeling. In this paper we take a decision theoretic...
Ofer Dekel, Shai Shalev-Shwartz, Yoram Singer