the ability to learn spatial relations is a prerequisite for performing many relevant tasks such as those associated with motion, orientation, navigation, etc. this paper reports on using a relational machine learning...
详细信息
this paper proposes new architecture of agent which adapts its behavior by predicting the results of actions and avoiding taking ones predicted to be failures shown in Fig. 1. Our agent consists of five parts: Observe...
ISBN:
(纸本)3540679251
this paper proposes new architecture of agent which adapts its behavior by predicting the results of actions and avoiding taking ones predicted to be failures shown in Fig. 1. Our agent consists of five parts: Observer, Planner, Actor which are same as those of basic agent and write perceiving information in the first-order formalism, Learner which acquires prediction rules using inductivelogicprogramming (ilp), and Checker which predicts the result of an action selected by Planner and changes action if it seems to be failure. the agent classifies past actions into successes and failures, then it learns rules from them to assort the current action without information after taking it.
the proceedings contain 121 papers. the special focus in this conference is on Foundations of AI, Induction, logicprogramming, Reinforcement Learning and Machine Learning. the topics include: Knowledge representation...
ISBN:
(纸本)3540679251
the proceedings contain 121 papers. the special focus in this conference is on Foundations of AI, Induction, logicprogramming, Reinforcement Learning and Machine Learning. the topics include: Knowledge representation, belief revision, and the challenge of optimality;towards a next-generation search engine;an attempt to represent a database by predicate formulae;a unifying semantics for causal ramifications;inductive inference of chess player strategy;compiling logical features into specialized state-evaluators by partial evaluation, Boolean tables and incremental calculation;using domain knowledge in ilp to discover protein functional models;knowledge reformation for efficient first-order hypothetical reasoning;determination of general concept in learning default rules;a theory of profit sharing in dynamic environment;a region selecting method which performs observation and action in the multi-resolution environment;the lumberjack algorithm for learning linked decision forests;efficient iris recognition system by optimization of feature vectors and classifier;an efficient learning algorithm using natural gradient and second order information of error surface;fast and robust general purpose clustering algorithms;tropical cyclone intensity forecasting model;trading off granularity against complexity in predictive models for complex domains;efficient inference in dynamic belief networks with variable temporal resolution;epistemic states guiding the rational dynamics of information;perceiving environments for intelligent agents;constructing an autonomous agent with an interdependent heuristics;from brain theory to autonomous robotic agents and a multi-agent approach for optical inspection technology.
We introduce a new reconfigurable logic element. Its operations are based on threshold logic and it can store its own configuration data. the element is composed of threshold gates which are implemented in a two-level...
详细信息
作者:
Sasaki, YNTT
Commun Sci Labs Seika Kyoto 6190237 Japan
this paper extends the traditional inductivelogicprogramming (ilp) framework to a psi-term capable ilp framework. Ait-Kaci's psi-terms have interesting and significant properties for markedly widening applicable...
详细信息
ISBN:
(纸本)3540667482
this paper extends the traditional inductivelogicprogramming (ilp) framework to a psi-term capable ilp framework. Ait-Kaci's psi-terms have interesting and significant properties for markedly widening applicable areas of ilp. For example, psi-terms allow partial descriptions of information, generalization and specialization of sorts (or types) placed instead of function symbols, and abstract descriptions of data using sorts;they have comparable representation power to feature structures used in natural language processing. We have developed an algorithm that learns logic programs based on psi-terms, made possible by a bottom-up approach employing the least general generalization (lgg) extended for psi-terms. As an area of application, we have selected information extraction (IE) tasks in which sort information is crucial in deciding the generality of IE rules. Experiments were conducted on a set of test examples and background knowledge consisting of case frames of newspaper articles. the results showed high precision and recall rates for learned rules for the IE tasks.
the proceedings contain 28 papers. the special focus in this conference is on Computer Science logic. the topics include: Four-valued diagnoses for stratified knowledge-bases;on the subject reduction property for alge...
ISBN:
(纸本)3540631720
the proceedings contain 28 papers. the special focus in this conference is on Computer Science logic. the topics include: Four-valued diagnoses for stratified knowledge-bases;on the subject reduction property for algebraic type systems;bounded-variable fixpoint queries are PSPACE-complete;graph rewriting semantics for functional programming languages;an extension of models of axiomatic domain theory to models of synthetic domain theory;relative undecidability in term rewriting;extending models of second order predicate logic to models of second order dependent type theory;cut-free display calculi for relation algebras;computational aspects of arity hierarchies;weak semantics based on lighted button pressing experiments;monadic NP and built-in trees;optimization problems with approximation schemes;computational representations of herbrand models using grammars;social confluence in client-server systems;a type-free resource-aware a-calculus;inductive definitions with decidable atomic formulas;new intuitionistic logical constants and undecidability of the conservativeness problem.
the proceedings contain 60 papers. the special focus in this conference is on logic for AI, Learning and Discovery Systems. the topics include: Goal-oriented multimedia dialogue with variable initiative;knowledge-base...
ISBN:
(纸本)3540636145
the proceedings contain 60 papers. the special focus in this conference is on logic for AI, Learning and Discovery Systems. the topics include: Goal-oriented multimedia dialogue with variable initiative;knowledge-based image retrieval with spatial and temporal constructs;verification and validation of AI systems that control deep-space spacecraft;data mining and knowledge discovery;embedding prioritized circumscription in logic programs;extending temporal logic for capturing evolving behaviour;a description logic model for querying knowledge bases for structured documents;refining first order theories with neural networks;a way of increasing both autonomy and versatility of a KDD system;a comparison of attribute selection strategies for attribute-oriented generalization;boolean reasoning for feature extraction problems;world model construction in children during physics learning;well-behaved evaluation functions for numerical attributes;an improved inductive learning algorithm with a preanalysis of data;efficient induction of numerical constraints;learning english syllabification for words;towards conceptual query answering;an implementation platform for query-answering in default logics;automating spoken dialogue systems;handwritten digit recognition by local principal components analysis;from conceptual model to internal model;speeding GA-based attribute selection for image interpretation;using recurrent selection to improve GA performance;a coevolutionary approach to concept learning;representation of music in a learning classifier system;on multi-class problems and discretization in inductivelogicprogramming and discovering empirical equations from robot-collected data.
暂无评论