Sciweavers

NIPS
2008
14 years 29 days ago
An ideal observer model of infant object perception
Before the age of 4 months, infants make inductive inferences about the motions of physical objects. Developmental psychologists have provided verbal accounts of the knowledge tha...
Charles Kemp, Fei Xu
NIPS
2008
14 years 29 days ago
Counting Solution Clusters in Graph Coloring Problems Using Belief Propagation
We show that an important and computationally challenging solution space feature of the graph coloring problem (COL), namely the number of clusters of solutions, can be accurately...
Lukas Kroc, Ashish Sabharwal, Bart Selman
NIPS
2008
14 years 29 days ago
Estimating vector fields using sparse basis field expansions
We introduce a novel framework for estimating vector fields using sparse basis field expansions (S-FLEX). The notion of basis fields, which are an extension of scalar basis functi...
Stefan Haufe, Vadim V. Nikulin, Andreas Ziehe, Kla...
NIPS
2008
14 years 29 days ago
Deep Learning with Kernel Regularization for Visual Recognition
In this paper we aim to train deep neural networks for rapid visual recognition. The task is highly challenging, largely due to the lack of a meaningful regularizer on the functio...
Kai Yu, Wei Xu, Yihong Gong
NIPS
2008
14 years 29 days ago
The Infinite Factorial Hidden Markov Model
We introduce a new probability distribution over a potentially infinite number of binary Markov chains which we call the Markov Indian buffet process. This process extends the IBP...
Jurgen Van Gael, Yee Whye Teh, Zoubin Ghahramani
NIPS
2008
14 years 29 days ago
Analyzing human feature learning as nonparametric Bayesian inference
Almost all successful machine learning algorithms and cognitive models require powerful representations capturing the features that are relevant to a particular problem. We draw o...
Joseph Austerweil, Thomas L. Griffiths
NIPS
2008
14 years 29 days ago
Dependent Dirichlet Process Spike Sorting
In this paper we propose a new incremental spike sorting model that automatically eliminates refractory period violations, accounts for action potential waveform drift, and can ha...
Jan Gasthaus, Frank Wood, Dilan Görür, Y...
NIPS
2008
14 years 29 days ago
Optimization on a Budget: A Reinforcement Learning Approach
Many popular optimization algorithms, like the Levenberg-Marquardt algorithm (LMA), use heuristic-based "controllers" that modulate the behavior of the optimizer during ...
Paul Ruvolo, Ian R. Fasel, Javier R. Movellan
NIPS
2008
14 years 29 days ago
Algorithms for Infinitely Many-Armed Bandits
We consider multi-armed bandit problems where the number of arms is larger than the possible number of experiments. We make a stochastic assumption on the mean-reward of a new sel...
Yizao Wang, Jean-Yves Audibert, Rémi Munos
NIPS
2008
14 years 29 days ago
Rademacher Complexity Bounds for Non-I.I.D. Processes
This paper presents the first Rademacher complexity-based error bounds for noni.i.d. settings, a generalization of similar existing bounds derived for the i.i.d. case. Our bounds ...
Mehryar Mohri, Afshin Rostamizadeh