- Autor
- Hauke Krzysztof
- Tytuł
- Maszynowe uczenie się w sensie rozbudowy bazy wiedzy
Machine Learning in Building Knowledge Base - Źródło
- Prace Naukowe Akademii Ekonomicznej we Wrocławiu, 1994, nr 683, s. 37-43, bibliogr. 5 poz.
- Tytuł własny numeru
- Informatyka
- Słowa kluczowe
- Sztuczna inteligencja, Automatyczne uczenie się, Systemy z bazą wiedzy, Systemy ekspertowe, Proces uczenia się
Artificial intelligence, Automatic learning, Knowledge based systems, Expert systems, Learning process - Uwagi
- summ.
- Abstrakt
- Autor zajmuje się ograniczeniami obecnych metod sztucznej inteligencji i przewidywaniami w zakresie kierunku rozwoju badań w tym zakresie.
Artificial intelligence (AI) is now experiencing extraordinary growth, and applications of its ideas and methods are appearing in many fields. Among its most visible and important successes are the development of expert systems, practical implementations of natural language-understanding systems, significant advances in computer vision and speech understanding, and new insights into building powerful inference systems. This rapid expansion of activities in AI leads one to believe that new successes are forthcoming.
In this context, it is important to ask what the limitations of the current methods are and what new directions research in this field should take. One of the obvious limitations, and hence a direction for further research, relates to machine learning - a field concerned with developing computational theories of learning and constructing learning systems.
Except for experimental programs developed in the course of machine learning research, current AI systems have very limited learning abilities or none at all. All of their knowledge must be programmed into them. When they contain, an error, they cannot correct it on their own; they will repeat it endlessly, no matter how many times the procedure is executed. They can neither improve gradually with experience nor learn domain knowledge by experimentation. They cannot automatically generate their algorithms, formulate new abstractions, or develop new solutions by drawing analogies to old ones, or through discovery. Generally speaking, these systems lack the ability to draw inductive inferences from information given to them. One might say that almost all current AI systems are deductive, as they are able to draw conclusions from knowledge incorporated and/or supplied to them, but they cannot acquire or generate new knowledge on their own. (original abstract) - Dostępne w
- Biblioteka Główna Uniwersytetu Ekonomicznego w Krakowie
Biblioteka SGH im. Profesora Andrzeja Grodka
Biblioteka Główna Uniwersytetu Ekonomicznego w Poznaniu
Biblioteka Główna Uniwersytetu Ekonomicznego we Wrocławiu - Bibliografia
-
- Berkson W., Wettersten J.: Learning from Error Open. Open Court Publishing Company, La Salle 1984.
- Kowalski R.: Logika w systemach ekspertowych. Część 1. "Informatyka", nr 5, 1987.
- Kowalski R. : Logika w systemach ekspertowych. Część 2. "Informatyka", nr 6, 1987.
- Michalski R.S.: O naturze uczenia się - problemy i kierunki badawcze. "Informatyka" nr 2, 1988.
- Michalski R.S., Carbonell J.G., Mitchell T.M.: Machine learning. Vol. 2. Morgan and Kaufmann Publishers, 1986.
- Cytowane przez
- ISSN
- 0324-8445
- Język
- pol
