Sciweavers

31 search results - page 3 / 7
» icann 2001
Sort
View
ICANN
2001
Springer
13 years 10 months ago
The Bayesian Committee Support Vector Machine
Empirical evidence indicates that the training time for the support vector machine (SVM) scales to the square of the number of training data points. In this paper, we introduce the...
Anton Schwaighofer, Volker Tresp
ICANN
2001
Springer
13 years 10 months ago
Product Unit Neural Networks with Constant Depth and Superlinear VC Dimension
Abstract. It has remained an open question whether there exist product unit networks with constant depth that have superlinear VC dimension. In this paper we give an answer by cons...
Michael Schmitt
ICANN
2001
Springer
13 years 10 months ago
Using Depressing Synapses for Phase Locked Auditory Onset Detection
Auditory onsets are robust features of sounds: because the direct path from sound source to ear is the shortest path, the onset is unaffected by reverberation. Many cells in the c...
Leslie S. Smith
ICANN
2001
Springer
13 years 10 months ago
Scalable Kernel Systems
Kernel-based systems are currently very popular approaches to supervised learning. Unfortunately, the computational load for training kernel-based systems increases drastically wit...
Volker Tresp, Anton Schwaighofer
ICANN
2001
Springer
13 years 10 months ago
Market-Based Reinforcement Learning in Partially Observable Worlds
Unlike traditional reinforcement learning (RL), market-based RL is in principle applicable to worlds described by partially observable Markov Decision Processes (POMDPs), where an ...
Ivo Kwee, Marcus Hutter, Jürgen Schmidhuber