Catálogo de publicaciones - libros

The research described in this paper focuses on global tempo transformations of monophonic audio recordings of saxophone jazz performances. More concretely, we have investigated the problem of how a performance played at a particular tempo can be automatically rendered at another tempo while preserving its expressivity. To do so we have develppoped a case-based reasoning system called . The results we have obtained have been extensively compared against a standard technique called uniform time stretching (UTS), and show that our approach is superior to UTS.

The Psi theory of human action regulation is a candidate for a cognitive architecture that tackles the problem of the interrelation of motivation and emotion with cognitive processes. We have transferred this theory into a cognitive modeling framework, implemented as an AI architecture, called MicroPsi. Here, we describe the main assumptions of the Psi theory and summarize a neural prototyping algorithm that matches perceptual input to hierarchical declarative representations.

In this article, we propose the design of sensory motor level as part of a three-layered agent architecture inspired from the Multilevel Process Theory of Emotion (Leventhal 1979, 1980; Leventhal and Scherer, 1987). Our project aims at modeling emotions on an autonomous embodied agent, a more robust robot than our previous prototype. Our robot has been equipped with sonar and vision for obstacle avoidance as well as vision for face recognition, which are used when she roams around the hallway to engage in social interactions with humans. The sensory motor level receives and processes inputs and produces emotion-like states without any further willful planning or learning. We describe: (1) the psychological theory of emotion which inspired our design, (2) our proposed agent architecture, (3) the needed hardware additions that we implemented on the commercialized ActivMedia’s robot, (4) the robot’s multi-modal interface designed especially to engage humans in natural (and hopefully pleasant) social interaction, and finally (5) our future research efforts.

The desire to share and reuse knowledge has led to the establishment of the Web Ontology Language (OWL) knowledge representation language. The Naturnet-Redime project needs to share qualitative knowledge models of issues relevant to sustainable development and OWL seems the obvious choice for representing such models to allow search and other activities relevant to sharing knowledge models. However, although the design choices made in OWL are properly documented, their implications for Artificial Intelligence (AI) are part of ongoing research. This paper explores the expressiveness of OWL by formalising the vocabulary and models used in Qualitative Reasoning (QR), and the applicability of OWL reasoners to solve QR problems. A parser has been developed to export (and import) the QR representations to (and from) OWL representations. To create the OWL definitions of the QR vocabulary and models, existing OWL patterns were used as much as possible. However, some new patterns, and pattern modifications, had to be developed in order to represent the QR vocabulary and models using OWL.

‘Query relaxation’ is one of the basic approaches to deal with unfulfillable or conflicting customer requirements in content-based recommender systems: When no product in the catalog exactly matches the customer requirements, the idea is to retrieve those products that fulfill as many of the requirements as possible by removing (relaxing) parts of the original query to the catalog. In general, searching for such an ‘maximum succeeding subquery’ is a non-trivial task because a) the theoretical search space exponentially grows with the number of the subqueries and b) the allowed response times are strictly limited in interactive recommender applications.

In this paper, we describe new techniques for the fast computation of ‘user-optimal’ query relaxations: First, we show how the number of required database queries for determining an optimal relaxation can be limited to the number of given subqueries by evaluating the subqueries individually. Next, it is described how the problem of finding relaxations returning ‘’ products can be efficiently solved by analyzing these partial query results in memory. Finally, we show how a general-purpose conflict detection algorithm can be applied for determining ‘preferred’ conflicts in interactive relaxation scenarios.

The described algorithms have been implemented and evaluated in a knowledge-based recommender framework; the paper comprises a discussion of implementation details, experiences, and experimental results.

We present an approach for solving proportional analogies of the form : :: : where a plausible outcome for is computed. The core of the approach is –Generalization. The generalization method is based on the extraction of the greatest common structure of the terms , and and yields a mapping to compute every possible value for with respect to some equational theory. This approach to analogical reasoning is formally sound and powerful and at the same time models crucial aspects of human reasoning, that is the guidance of mapping by shared roles and the use of re-representations based on a background theory. The focus of the paper is on the presentation of the approach. It is illustrated by an application for the letter string domain.

A new approach to building robots with anticipatory behavior is presented. This approach is based on analogy with a single episode from the past experience of the robot. The AMBR model of analogy-making is used as a basis, but it is extended with new agent-types and new mechanisms that allow anticipation related to analogical transfer. The role of selective attention on retrieval of memory episodes is tested in a series of simulations and demonstrates the context sensitivity of the AMBR model. The results of the simulations clearly demonstrated that endowing robots with analogy-based anticipatory behavior is promising and deserves further investigation.

In this paper, we examine the performance of the two policies for keyword selection over standard document corpora of varying properties. While in corpus-based policy a single set of keywords is selected for all classes globally, in class-based policy a distinct set of keywords is selected for each class locally. We use SVM as the learning method and perform experiments with boolean and tf-idf weighting. In contrast to the common belief, we show that using keywords instead of all words generally yields better performance and tf-idf weighting does not always outperform boolean weighting. Our results reveal that corpus-based approach performs better for large number of keywords while class-based approach performs better for small number of keywords. In skewed datasets, class-based keyword selection performs consistently better than corpus-based approach in terms of macro-averaged F-measure. In homogenous datasets, performances of class-based and corpus-based approaches are similar except for small number of keywords.

Building or learning semantic parsers has been an interesting approach for creating natural language interfaces (NLI’s) for databases. Recently, the problem of imperfect precision in an NLI has been brought up as an NLI that might answer a question incorrectly can render it unstable, if not useless. In this paper, an approach based on ensemble learning is proposed to trivially address the problem of unreliability in an NLI due to imperfect precision in the semantic parser in a way that also allows the recall of the NLI to be improved. Experimental results in two real world domains suggested that such an approach can be promising.

We present the agent programming language POGTGolog, which integrates explicit agent programming in Golog with game-theoretic multi-agent planning in partially observable stochastic games. It deals with the case of one team of cooperative agents under partial observability, where the agents may have different initial belief states and not necessarily the same rewards. POGTGolog allows for specifying a partial control program in a high-level logical language, which is then completed by an interpreter in an optimal way. To this end, we define a formal semantics of POGTGolog programs in terms of Nash equilibria, and we specify a POGTGolog interpreter that computes one of these Nash equilibria. We illustrate the usefulness of POGTGolog along a rugby scenario.