Sciweavers

225 search results - page 38 / 45
» Knowledge Representation and Possible Worlds for Neural Netw...
Sort
View
NDJFL
2000
79views more  NDJFL 2000»
13 years 7 months ago
An Information-Based Theory of Conditionals
We present an approach to combining three areas of research which we claim are all based on information theory: knowledge representation in Artificial Intelligence and Cognitive Sc...
Wayne Wobcke
CLEIEJ
2007
152views more  CLEIEJ 2007»
13 years 7 months ago
Gene Expression Analysis using Markov Chains extracted from RNNs
Abstract. This paper present a new approach for the analysis of gene expression, by extracting a Markov Chain from trained Recurrent Neural Networks (RNNs). A lot of microarray dat...
Igor Lorenzato Almeida, Denise Regina Pechmann Sim...
IJCAI
2007
13 years 8 months ago
A Fully Connectionist Model Generator for Covered First-Order Logic Programs
We present a fully connectionist system for the learning of first-order logic programs and the generation of corresponding models: Given a program and a set of training examples,...
Sebastian Bader, Pascal Hitzler, Steffen Höll...
AIPS
2000
13 years 8 months ago
New Advances in GraphHTN: Identifying Independent Subproblems in Large HTN Domains
We describe in this paper a new method for extracting knowledge on Hierarchical Task-Network (HTN) planning problems for speeding up the search. This knowledge is gathered by prop...
Amnon Lotem, Dana S. Nau
ICANN
2010
Springer
13 years 6 months ago
Teaching Humanoids to Imitate 'Shapes' of Movements
Trajectory formation is one of the basic functions of the neuromotor controller. In particular, reaching, avoiding, controlling impacts (hitting), drawing, dancing and imitating ar...
Vishwanathan Mohan, Giorgio Metta, Jacopo Zenzeri,...