Advances in Artificial Intelligence: 19th Conference of the by Luc Lamontagne, Mario Marchand

By Luc Lamontagne, Mario Marchand

This booklet constitutes the refereed court cases of the nineteenth convention of

the Canadian Society for  Computational reviews of Intelligence, Canadian

AI 2006, held in Québec urban, Québec, Canada in June 2006.

The forty seven revised complete papers awarded have been conscientiously reviewed and chosen

from 220 submissions. The papers are equipped in topical sections on

agents, bioinformatics, constraint delight and allotted seek,

knowledge illustration and reasoning, average language, reinforcement

learning and, supervised and unsupervised learning.

Show description

Read Online or Download Advances in Artificial Intelligence: 19th Conference of the Canadian Society for Computational Studies of Intelligence, Canadian AI 2006, Quebec City, PDF

Similar computational mathematicsematics books

Computational Nuclear Physics 2

This moment quantity of the sequence offers basically with nuclear reactions, and enhances the 1st quantity, which focused on nuclear constitution. offering discussions of either the proper physics in addition to the numerical equipment, the chapters codify the services of a number of the best researchers in computational nuclear physics.

Weather Prediction by Numerical Process

The assumption of forecasting the elements through calculation was once first dreamt of by way of Lewis Fry Richardson. the 1st variation of this publication, released in 1922, set out a close set of rules for systematic numerical climate prediction. the strategy of computing atmospheric alterations, which he mapped out in nice aspect during this ebook, is largely the strategy used at the present time.

Additional info for Advances in Artificial Intelligence: 19th Conference of the Canadian Society for Computational Studies of Intelligence, Canadian AI 2006, Quebec City,

Example text

One of the major difficulties inherent to cognitive assistance is to identify the on-going inhabitant ADL from observed basic actions. This problem is known as plan recognition in the field of artificial intelligence [7]. The problem of plan recognition can be basically synthesized by the need “. . to take as input a sequence of actions performed by an actor and to infer the goal pursued by the actor and also to organize the action sequence in terms of a plan structure” [15]. Thus, the main objective is to predict the behaviour of the observed agent.

Bouzouane suppose that a second observation GetW ater(o2 ) was detected. The new interpretation model would then be the sub-lattice upper bounded by P repareT ea and lower bounded by W ashDishΔP repareT ea, as shown in Figure 2. Let us now suppose that the assistant agent has detected that the inhabitant remains still for a certain period of time. In such a case, the assistant agent will have to increase his autonomy level by taking control of the home using the intention schema of the inhabitant, defined by the infinimum Δinf = (x ◦ GoT oKitchen) of the lattice, to predict what the person wanted to do.

Then, it chooses the best action to perform. In order to facilitate the understanding of the map and adapt its content to users’ expectations, we propose to emphasize the objects which are important to the user by using multiple representations: graphic, semantic, and geometric representations (Fig. 3). Thus, the goal of every agent is to guarantee legible representations of the object it is assigned to. When attempting to reach this goal, conflicts may appear due to the lack of space. In order to shorten the negotiation time necessary to solve these conflicts, we propose the following conflict resolution pattern (Fig.

Download PDF sample

Rated 4.37 of 5 – based on 49 votes