ChapterPDF Available

L'Intelligenza Artificiale: la storia e le idee

Authors:
Roberto Cordeschi at Sapienza University of Rome
Roberto Cordeschi
Guglielmo Tamburrini at University of Naples Federico II
Guglielmo Tamburrini
Download full-text PDFDownload full-text PDF
Read full-text
Download citation

Abstract

Scopo di questo capitolo è di introdurre il lettore ai principali argomenti che, nel corso della sua breve storia, l’Intelligenza Artificiale (IA) ha affrontato sia nella variante applicativa o ingegneristica sia in quella teorica o cognitiva. Alla fine di questo capitolo il lettore dovrebbe – avere presente l’evoluzione di alcune delle tendenze di ricerca più influenti in IA; – essere al corrente delle più recenti posizioni nel dibattito attuale all’interno dell’ IA; – essere brevemente introdotto ad alcuni classici problemi filosofici ed epistemologici affrontati dall’IA.
554bdf680cf21ed2135b7b
00.pdf
Content uploaded by Guglielmo Tamburrini
Author content
All content in this area was uploaded by Guglielmo Tamburrini on May 07, 2015
Content may be subject to copyright.
Manuale IA Cap.
1.pdf
Content uploaded by Roberto Cordeschi
Author content
All content in this area was uploaded by Roberto Cordeschi
Content may be subject to copyright.
A preview of the PDF is not available
Alan Turing e il programma di ricerca dell'Intelligenza Artificiale
Chapter
Full-text available
  • Dec 2015
E’ riduttivo e per alcuni aspetti anche fuorviante incentrare sul cosiddetto “gioco dell’imitazione”, noto anche come Test di Turing (TT), l’analisi dei contributi di Alan Turing alla nascita e allo sviluppo iniziale dell’Intelligenza Artificiale (IA). Anzitutto, la funzione intesa del TT sembra essere stata fin dall’inizio puramente divulgativa: Turing aveva l’obiettivo di raggiungere un ampio pubblico di persone colte, alle quali trasmettere e illustrare la possibilità tecnologica di sviluppare macchine capaci di elaborare strutture simboliche e di manifestare comportamenti intelligenti, Inoltre, le regole proposte per la conduzione e il superamento del TT risultano essere molto vaghe, senza peraltro soddisfare i requisiti di intersoggettività per la valutazione dei risultati di un test empirico. E’ infine rilevante il dato di fatto che il TT non sia stato usato come benchmark o test empirico per i sistemi concretamente sviluppati dall’IA. L’obiettivo di superare il TT—qualunque cosa si intenda con ciò—è stato perseguito prevalentemente in manifestazioni socio-culturali, come il Loebner Prize, Ciononostante, è piuttosto diffusa la strategia di incentrare proprio intorno al TT il discorso sul rapporto tra Turing e l’IA. In questo lavoro proponiamo una diversa strategia per analizzare le relazioni tra Turing e l’IA, soprattutto in considerazione della sostanziale estraneità del TT allo svolgimento effettivo delle ricerche condotte nell’ambito dell’IA. Ecco in breve che cosa ci proponiamo di fare: partendo da una ricostruzione schematica dell’IA vista come un programma di ricerca, metteremo in evidenza i contributi di carattere modellistico, epistemologico, metodologico e anche tecnologico che Turing ha dato al suo sviluppo.
View
View
View
Meta-learning and Neurocomputing – A New Perspective for Computational Intelligence
Chapter
  • Feb 2009
In this chapter an analysis of computational mechanisms of induction is brought forward, in order to assess the potentiality of meta-learning methods versus the common base-learning practices. To this aim, firstly a formal investigation of inductive mechanisms is accomplished, sketching a distinction between fixed and dynamical bias learning. Then a survey is presented with suggestions and examples which have been proposed in literature to increase the efficiency of common learning algorithms. The peculiar laboratory for this kind of investigation is represented by the field of connectionist learning. To explore the meta-learning possibilities of neural network systems, knowledge-based neurocomputing techniques are considered. Among them, some kind of hybridisation strategies are particularly analysed and addressed as peculiar illustrations of a new perspective of Computational Intelligence.
View
Foundations of Computational Intelligence Volume 1: Learning and Approximation
Chapter
  • Jan 2009
Learning methods and approximation algorithms are fundamental tools that deal with computationally hard problems and problems in which the input is gradually disclosed over time. Both kinds of problems have a large number of applications arising from a variety of fields, such as algorithmic game theory, approximation classes, coloring and partitioning, competitive analysis, computational finance, cuts and connectivity, geometric problems, inapproximability results, mechanism design, network design, packing and covering, paradigms for design and analysis of approximation and online algorithms, randomization techniques, real-world applications, scheduling problems and so on. The past years have witnessed a large number of interesting applications using various techniques of Computational Intelligence such as rough sets, connectionist learning; fuzzy logic; evolutionary computing; artificial immune systems; swarm intelligence; reinforcement learning, intelligent multimedia processing etc.. In spite of numerous successful applications of Computational Intelligence in business and industry, it is sometimes difficult to explain the performance of these techniques and algorithms from a theoretical perspective. Therefore, we encouraged authors to present original ideas dealing with the incorporation of different mechanisms of Computational Intelligent dealing with Learning and Approximation algorithms and underlying processes.
View
View
On computation and cognition: Toward a foundation of cognitive science
Article
  • Mar 1989
  • ARTIF INTELL
The question, "What is Cognitive Science?" is often asked but seldom answered to anyone's satisfaction. Until now, most of the answers have come from the new breed of philosophers of mind. This book, however, is written by a distinguished psychologist and computer scientist who is well-known for his work on the conceptual foundations of cognitive science, and especially for his research on mental imagery, representation, and perception. In Computation and Cognition, Pylyshyn argues that computation must not be viewed as just a convenient metaphor for mental activity, but as a literal empirical hypothesis. Such a view must face a number of serious challenges. For example, it must address the question of "strong equivalents" of processes, and must empirically distinguish between phenomena which reveal what knowledge the organism has, phenomena which reveal properties of the biologically determined "functional architecture" of the mind. The principles and ideas Pylyshyn develops are applied to a number of contentious areas of cognitive science, including theories of vision and mental imagery. In illuminating such timely theoretical problems, he draws on insights from psychology, theoretical computer science, artificial intelligence, and psychology of mind. A Bradford Book
View
View
View
View
Behavior, Purpose and Teleology
Article
  • Jan 1943
This essay has two goals. The first is to define the behavioristic study of natural events and to classify behavior. The second is to stress the importance of the concept of purpose. Given any object, relatively abstracted from its surroundings for study, the behavioristic approach consists in the examination of the output of the object and of the relations of this output to the input. By output is meant any change produced in the surroundings by the object. By input, conversely, is meant any event external to the object that modifies this object in any manner.
View
The Role of Models in Science
Article
  • Jan 1945
The intention and the result of a scientific inquiry is to obtain an understanding and a control of some part of the universe. This statement implies a dualistic attitude on the part of scientists. Indeed, science does and should proceed from this dualistic basis. But even though the scientist behaves dualistically, his dualism is operational and does not necessarily imply strict dualistic metaphysics.
View
The Discovery of the Artificial
Article
  • Jan 2002
This series will include monographs and collections of studies devoted to the investigation and exploration of knowledge, information, and data processing systems of all kinds, no matter whether human, (other) animal, or machine. Its scope is intended to span the full range of interests from classical problems in the philosophy of mind and philosophical psychology through issues in cognitive psychology and sociobiology (concerning the mental capabilities of other species) to ideas related to artificial intelligence and to computer science. While primary emphasis will be placed upon theoretical, conceptual, and epistemological aspects of these problems and domains, empirical, experimental, and methodological studies will also appear from time to time. The present volume offers a broad and imaginative approach to the study of the mind, which emphasizes several themes, namely: the importance of functional organization apart from the specific material by means of which it may be implemented; the use of modeling to simulate these functional processes and subject them to certain kinds of tests; the use of mentalistic language to describe and predict the behavior of artifacts; and the subsumption of processes of adaptation, learning, and intelligence by means of explanatory principles. The author has produced a rich and complex, lucid and readable discussion that clarifies and illuminates many of the most difficult problems arising within this difficult domain.
View
Case Studies in Cognitive Robotics
Article
  • Jan 2001
Cognitive Robotics is concerned with the theory and implementation of embodied intelligent agents. Cognitive Robotics poses a unique challenge to researchers: it deals in fact with manufacts that are inherently autonomous, situated in a not structured environment, and whose behavior is characterized by a cycle “Perception-Reasoning-Action” or “Sense-Plan-Act” (sometimes called SPA architectures). Of course this cycle has to be performed reliably, and in real time. Sensing, planning and acting are difficult problems to be solved, per se. Their integration within a single system poses additional challenges.
View
The notion of loop in the study of consciousness
Conference Paper
  • May 1999
The notion of loop seems to be ubiquitous in the study of organisms, the human mind and symbolic systems. With the possible exception of quantum-mechanical approaches, the treatments of consciousness we are acquainted with crucially appeal to the concept of loop. The uses of loops in this context fall within two broad classes. In the first one, loops are used to express the control of the organism’s interaction with the environment; in the second one, they are used to express self-reference. Both classes are tied with investigations which aim at accounting for symbolic capabilities, and ultimately for subjectivity. Neurophysiological research detects loops in the animal nervous system since its very inception (e.g., all the work on the reflex arc). Recently, Gray proposed a model purporting to explain the mechanism supporting the contents of consciousness in the human CNS, in ways that are practically indistinguishable from models formulated within the cybernetical point of view. Both types of models apply loops in strikingly similar ways. While there is no conclusive evidence that loops are necessary to support consciousness, they are nonetheless as good a candidate as today can be found for inclusion in the list of essential ingredients for subjectivity to arise. In the first two sections we discuss the above mentioned uses by means of significant examples. In the third section, we compare Gray’s recent model to MacKay’s early cybernetical model of a selfobserving system, in the setting of a broader discussion on loops for consciousness.
View