Sciweavers

15 search results - page 2 / 3
» Improving Recurrent Neural Network Performance Using Transfe...
Sort
View
FLAIRS
2010
13 years 7 months ago
CsMTL MLP For WEKA: Neural Network Learning with Inductive Transfer
We present context-sensitive Multiple Task Learning, or csMTL as a method of inductive transfer. It uses additional contextual inputs along with other input features when learning ...
Liangliang Tu, Benjamin Fowler, Daniel L. Silver
GECCO
2011
Springer
256views Optimization» more  GECCO 2011»
12 years 8 months ago
Evolving complete robots with CPPN-NEAT: the utility of recurrent connections
This paper extends prior work using Compositional Pattern Producing Networks (CPPNs) as a generative encoding for the purpose of simultaneously evolving robot morphology and contr...
Joshua E. Auerbach, Josh C. Bongard
ICASSP
2011
IEEE
12 years 8 months ago
A multi-stream ASR framework for BLSTM modeling of conversational speech
We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...
Martin Wöllmer, Florian Eyben, Björn Sch...
ICANN
2010
Springer
13 years 4 months ago
Multi-Dimensional Deep Memory Atari-Go Players for Parameter Exploring Policy Gradients
Abstract. Developing superior artificial board-game players is a widelystudied area of Artificial Intelligence. Among the most challenging games is the Asian game of Go, which, des...
Mandy Grüttner, Frank Sehnke, Tom Schaul, J&u...
GECCO
1999
Springer
133views Optimization» more  GECCO 1999»
13 years 9 months ago
Evolution of Goal-Directed Behavior from Limited Information in a Complex Environment
In this paper, we apply an evolutionary algorithm to learning behavior on a novel, interesting task to explore the general issue of learning e ective behaviors in a complex enviro...
Matthew R. Glickman, Katia P. Sycara