Sciweavers

IJCAI
1997
13 years 5 months ago
Extracting Propositions from Trained Neural Networks
This paper presents an algorithm for extract­ ing propositions from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural networ...
Hiroshi Tsukimoto
IJCAI
1997
13 years 5 months ago
Computational Complexity of Multi-way, Dataflow Constraint Problems
Although it is acknowledged that multi-way dataflow constraints are useful in interactive applications, concerns about their tractability have hindered their acceptance. Certain l...
Gilles Trombettoni, Bertrand Neveu
IJCAI
1997
13 years 5 months ago
An Effective Learning Method for Max-Min Neural Networks
Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ m...
Loo-Nin Teow, Kia-Fock Loe
IJCAI
1997
13 years 5 months ago
Exploiting Domain Knowledge for Approximate Diagnosis
The AI literature contains many definitions of diagnostic reasoning most of which are defined in terms of the logical entailment relation. We use existing work on approximate en...
Annette ten Teije, Frank van Harmelen
IJCAI
1997
13 years 5 months ago
A Four-Valued Fuzzy Propositional Logic
It is generally accepted that knowledge based systems would be smarter and more robust if they can manage inconsistent, incomplete or imprecise knowledge. This paper is about a fo...
Umberto Straccia
IJCAI
1997
13 years 5 months ago
The Origins of Syntax in Visually Grounded Robotic Agents
The paper proposes a set of principles and a general architecture that may explain how language and meaning may originate and complexify in a group of physically grounded distribu...
Luc Steels
IJCAI
1997
13 years 5 months ago
A Symmetric View of Utilities and Probabilities
Motivated by the need to reason about utilities, and inspired by the success of bayesian networks in representing and reasoning about probabilities, we introduce the notion of uti...
Yoav Shoham
IJCAI
1997
13 years 5 months ago
Combining Knowledge Acquisition and Machine Learning to Control Dynamic Systems
This paper presents an interactive method for building a controller for dynamic systems by using a combination of knowledge acquisition and machine learning techniques. The aim is...
G. M. Shiraz, Claude Sammut
IJCAI
1997
13 years 5 months ago
Learning Topological Maps with Weak Local Odometric Information
cal maps provide a useful abstraction for robotic navigation and planning. Although stochastic mapscan theoreticallybe learned using the Baum-Welch algorithm,without strong prior ...
Hagit Shatkay, Leslie Pack Kaelbling
IJCAI
1997
13 years 5 months ago
Ten Challenges in Propositional Reasoning and Search
The past several years have seen much progress in the area of propositional reasoning and satisfiability testing. There is a growing consensus by researchers on the key technical ...
Bart Selman, Henry A. Kautz, David A. McAllester