Obiekt

Tytuł: Abstraction based connectionist analogy processor

Autor:

Yasui, Syozo

Data wydania:

2000

Typ zasobu:

artykuł

Współtwórca:

Rutkowska, Danuta - ed. ; Zadeh, Lotfi A. - ed.

Podtytuł:

Neuro-Fuzzy and Soft Computing

Tytuł publikacji grupowej:

AMCS, volume 10 (2000)

Abstract:

The Abstraction Based Connectionist Analogy Processor (AB-CAP) is a trainable neural network for analogical learning/inference. An internal abstraction model, which extracts the underlying relational isomorphism and expresses predicate-argument bindings at the abstract level, is induced structurally as a result of the backpropagation training coupled with a structure-pruning mechanism. AB-CAP also develops dynamically abstraction and de-abstraction mappings for the role-filler matching. ; Thus, the propositions including both known and inferred ones can be expressed by, induced as, stored in and retrieved from the internal structural patterns. As such, there is no need for AB-CAP to use rule-based symbolic processing such as hypothesis making and constraint satisfaction or pattern completion checking. In this paper, AB-CAP is evaluated by using some examples. ; In particular, incremental analogical learning by AB-CAP shows that the internal abstraction model acquired from previous analogical learning acts as a potent attracter to bind a new set of isomorphic data, manifesting the analogical memory access/retrieval characteristics of AB-CAP.

Wydawca:

Zielona Góra: Uniwersytet Zielonogórski

Identyfikator zasobu:

oai:zbc.uz.zgora.pl:58749

Strony:

791-812

Źródło:

AMCS, volume 10, number 4 (2000) ; kliknij tutaj, żeby przejść

Jezyk:

eng

Prawa do dysponowania publikacją:

Biblioteka Uniwersytetu Zielonogórskiego

Obiekty

Podobne

Ta strona wykorzystuje pliki 'cookies'. Więcej informacji