You are here

Publications

Primary tabs

  1. R. Battiti; P. Lee; A. Sartori; Gian Pietro Tecchiolli,
    Combinatiorial Optimization for Neural Nets: RTS Algorithm and Silicon,
    The training of neural networks is considered as a combinatorial optimization task and solved with the Reactive Tabu Search (RTS) method. RTS is applicable to non-differentiable functions, is robust with respect to the random initialization and effective in exploring the search space. A special-purpose VLSI architecture was developed to take advantage of the limited memory and processing requirements of RTS. A brief description of the chip and a test on a recurrent network are presented,
  2. F. Marchetti; Silvia Girardi,
    Indagini chimico-fisiche su materiali pittorici prelevati da affreschi di casa Martini a Sarnonico,
  3. R. Fiutem,
    A Basic Socket Library: C Interface,
  4. A. Artale; E. Franconi; C. Bettini,
    Homogenous Concepts in a Temporal Description Logic,
  5. Bernardo Magnini; Carlo Strapparava; F. Ciravegna; Emanuele Pianta,
    A Project for the Construction of an Italian Lexical Knowledge Base in the Framework of WordNet,
    This paper describes a project that aims to develop a large-size Lexical Knowledge Base (LKB) for the Italian language. The project began because presently there is no LKB available for Italian, on an electronic support, that can be used both for natural language processing and lexicography applications. To develop the LKB techniques developed in artificial intelligence that allow acquisition and automatic data structuring will be used,
  6. Paolo Bouquet,
    A Mechanized Multi-Context Solution to McCarthy's GLM Problem,
    In this paper I present a context-based mechanization in GETFOL of the Glasgow-London-Moscow (GLM) problem, an instance of a more general problem called the qualification problem ([McC80]). The mechanization is based on a formalization of the GLM problem using multi-context systems (MC-systems) that is aimed to overcome some epistemological limitations of a previous formalization using circumscription. Though this approach solves many difficulties from a representational point of view, its mechanization raises some theoretical and practical problems that are not faced in the formalization. Since these problems don't depend on the particular example, their solution can be extended to context-based mechanizations of a broad class of problems,
  7. Paolo Bouquet; Fausto Giunchiglia,
    Reasoning about Theory Adequacy. A New Solution to the Qualification Problem,
    One of the main problems in commonsense reasoning is the qualification problem, ie. the fact that the number of qualifications for most general commonsense statements is virtually infinite. In this paper we argue that a solution to this problem should be based on a (meta) conjecture that the theory used to reason about the world contains all the necessary information. We also show that this theory adequacy conjecture can be made before the application of any of the formalisms proposed in the past, eg. circumscription. Finally, we present a formalization of the solution proposed using contexts and circumscription and use it to solve McCarthy's Glasgow-London-Moscow example,
  8. Bianca Angelini; Roberto Gretter,
    APASCI 1.0: acquisizione,
    Questo lavoro descrive le acquisizioni della base dati alla quale è stato dato il nome di APASCI [Ric92], un acronimo per Acoustic Phonetic And Spontaneous speech Corpus of IRST. APASCI comprende sia materiale vocale che possa garantire una copertura adeguata dei fenomeni acustici della lingua italiana, sia materiale spontaneo ottenuto durante simulazioni [FG91, CFGLar] in cui i soggetti credono di interagire con una macchina,
  9. F. Ciravegna,
    Estrazione di informazioni da testi: stato dell`arte e prospettive,
  10. Ornella Mich,
    Viewpoint Dependence in Face Recognition,
    This paper analyzes the problem of face recognition as a cognitive process. Specifically, it studies the influence of the angle from which the face to recognize is observed. Following the examination of studies that considered this problem in the past, two psychophysical experiments are presented that seek to further clarify the problem. It is shown that the subject gives different responses according to target viewpoint, with the surest and most rapid recognition coming from observation of the right-hand side of the face.,