Sciweavers

4181 search results - page 264 / 837
» Evaluating Usefulness for Dynamic Classification
Sort
View
EVOW
2003
Springer
15 years 9 months ago
Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs
Abstract. This paper explores the capabilities of continuous time recurrent neural networks (CTRNNs) to display reinforcement learning-like abilities on a set of T-Maze and double ...
Jesper Blynel, Dario Floreano
SERVICEWAVE
2010
15 years 2 months ago
Self-adapting Applications Based on QA Requirements in the Cloud Using Market-Based Heuristics
There are several situations where applications in the cloud need to self-manage their quality attributes (QA). We posit that selfadaptation can be achieved through a market-based ...
Vivek Nallur, Rami Bahsoon
NAACL
1994
15 years 5 months ago
Language Identification via Large Vocabulary Speaker Independent Continuous Speech Recognition
The goal of this study is to evaluate the potential for using large vocabulary continuous speech recognition as an engine for automatically classifying utterances according to the...
Steve Lowe, Anne Demedts, Larry Gillick, Mark Mand...
ICML
2005
IEEE
16 years 5 months ago
Predicting relative performance of classifiers from samples
This paper is concerned with the problem of predicting relative performance of classification algorithms. It focusses on methods that use results on small samples and discusses th...
Rui Leite, Pavel Brazdil
CHI
2007
ACM
16 years 5 months ago
Provoking sociability
In this study, we explore the potential usefulness of disturbing, uncomfortable systems, demonstrating that provocative technology can have a positive effect on social relationshi...
Brooke E. Foucault, Helena M. Mentis, Phoebe Senge...