Sciweavers

265 search results - page 37 / 53
» On the Computational Power of Neural Nets
Sort
View
CIBCB
2006
IEEE
16 years 4 days ago
Machine Learning in Basecalling Decoding Trace Peak Behaviour
— DNA sequence basecalling is commonly regarded as a solved problem, despite significant error rates being reflected in inaccuracies in databases and genome annotations. These er...
David Thornley, Stavros Petridis
GECCO
2005
Springer
220views Optimization» more  GECCO 2005»
15 years 11 months ago
Scale invariant pareto optimality: a meta--formalism for characterizing and modeling cooperativity in evolutionary systems
This article describes a mathematical framework for characterizing cooperativity in complex systems subject to evolutionary pressures. This framework uses three foundational compo...
Mark Fleischer
SSPR
2004
Springer
15 years 11 months ago
Clustering Variable Length Sequences by Eigenvector Decomposition Using HMM
We present a novel clustering method using HMM parameter space and eigenvector decomposition. Unlike the existing methods, our algorithm can cluster both constant and variable leng...
Fatih Murat Porikli
EVOW
2008
Springer
15 years 7 months ago
Scaffolding for Interactively Evolving Novel Drum Tracks for Existing Songs
Abstract. A major challenge in computer-generated music is to produce music that sounds natural. This paper introduces NEAT Drummer, which takes steps toward natural creativity. NE...
Amy K. Hoover, Michael P. Rosario, Kenneth O. Stan...
NECO
2007
115views more  NECO 2007»
15 years 5 months ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...