Please use this identifier to cite or link to this item:
Title: Linear algebra approach to neural associative memories and noise performance of neural classifiers
Authors: Βασιλάς, Νικόλαος
Cherkassky, Vladimir
Fassett, K.
Item type: Journal article
Keywords: Γραμμική Άλγεβρα;Νευρωνικές συνειρμικές μνήμες;Απόδοση θορύβου;Νευρωνικοί ταξινομητές;Linear algebra;Neural Associative Memories;Noise Performance;Neural Classifiers
Subjects: Πληροφορική
Μηχανική υπολογιστών
Computer science
Computer engineering
Issue Date: 11-May-2015
Abstract: The authors present an analytic evaluation of saturation and noise performance for a large class of associative memories based on matrix operations. The importance of using standard linear algebra techniques for evaluating noise performance of associative memories is emphasized. The authors present a detailed comparative analysis of the correlation matrix memory and the generalized inverse memory construction rules for auto-associative memory and neural classifiers. Analytic results for the noise performance of neural classifiers that can store several prototypes in one class are presented. The analysis indicates that for neural classifiers the simple correlation matrix memory provides better noise performance than the more complex generalized inverse memory.
Language: English
Citation: Cherkassky, V., Vassilas, N. and Fassett, K. (1991) Linear algebra approach to neural associative memories and noise performance of neural classifiers. IEEE Transactions on Computers. [Online] 40 (12), pp.1429-1435. Available from: [Accessed 10/05/2015]
Journal: IEEE Transactions on Computers
Type of Journal: With a review process (peer review)
Access scheme: Embargo
License: Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες
Appears in Collections:Δημοσιεύσεις

Files in This Item:
There are no files associated with this item.

This item is licensed under a Creative Commons License Creative Commons