Sciweavers

Share
NIPS
2004
9 years 12 months ago
Using Random Forests in the Structured Language Model
In this paper, we explore the use of Random Forests (RFs) in the structured language model (SLM), which uses rich syntactic information in predicting the next word based on words ...
Peng Xu, Frederick Jelinek
NIPS
2004
9 years 12 months ago
Brain Inspired Reinforcement Learning
Successful application of reinforcement learning algorithms often involves considerable hand-crafting of the necessary non-linear features to reduce the complexity of the value fu...
François Rivest, Yoshua Bengio, John Kalask...
NIPS
2004
9 years 12 months ago
An Information Maximization Model of Eye Movements
We propose a sequential information maximization model as a general strategy for programming eye movements. The model reconstructs high-resolution visual information from a sequen...
Laura Walker Renninger, James M. Coughlan, Preeti ...
NIPS
2004
9 years 12 months ago
Chemosensory Processing in a Spiking Model of the Olfactory Bulb: Chemotopic Convergence and Center Surround Inhibition
This paper presents a neuromorphic model of two olfactory signalprocessing primitives: chemotopic convergence of olfactory receptor neurons, and center on-off surround lateral inh...
Baranidharan Raman, Ricardo Gutierrez-Osuna
NIPS
2004
9 years 12 months ago
Conditional Random Fields for Object Recognition
We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts co...
Ariadna Quattoni, Michael Collins, Trevor Darrell
NIPS
2004
9 years 12 months ago
New Criteria and a New Algorithm for Learning in Multi-Agent Systems
We propose a new set of criteria for learning algorithms in multi-agent systems, one that is more stringent and (we argue) better justified than previous proposed criteria. Our cr...
Rob Powers, Yoav Shoham
NIPS
2004
9 years 12 months ago
VDCBPI: an Approximate Scalable Algorithm for Large POMDPs
Existing algorithms for discrete partially observable Markov decision processes can at best solve problems of a few thousand states due to two important sources of intractability:...
Pascal Poupart, Craig Boutilier
NIPS
2004
9 years 12 months ago
Active Learning for Anomaly and Rare-Category Detection
We introduce a novel active-learning scenario in which a user wants to work with a learning algorithm to identify useful anomalies. These are distinguished from the traditional st...
Dan Pelleg, Andrew W. Moore
NIPS
2004
9 years 12 months ago
Efficient Out-of-Sample Extension of Dominant-Set Clusters
Dominant sets are a new graph-theoretic concept that has proven to be relevant in pairwise data clustering problems, such as image segmentation. They generalize the notion of a ma...
Massimiliano Pavan, Marcello Pelillo
NIPS
2004
9 years 12 months ago
Approximately Efficient Online Mechanism Design
Online mechanism design (OMD) addresses the problem of sequential decision making in a stochastic environment with multiple self-interested agents. The goal in OMD is to make valu...
David C. Parkes, Satinder P. Singh, Dimah Yanovsky
books