The Brain & Neural Networks
Online ISSN : 1883-0455
Print ISSN : 1340-766X
ISSN-L : 1340-766X
Search
Advanced search
OR
Browse
Search
Volume 2, Issue 1
Displaying 1-12 of 12 articles from this issue
Show all abstracts
    • |<
    • <
    • 1
    • >
    • >|
  • One-shot Learning Algorithm Using Adaptive Similarity
    Kosei Demura, Yuichiro Anzai
    1995 Volume 2 Issue 1 Pages 4-10
    Published: March 05, 1995
    Released on J-STAGE: December 01, 2010
    DOIhttps://doi.org/10.3902/jnns.2.4
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    We have proposed the one-shot learning algorithm called SOLAR (Supervised One-shot Learning Algorithm for Real number inputs) which needs only a single presentation of training examples, and the learning speed is extremely fast. However, the generalization ability is not satisfactory. In this paper, we propose SOLAR 2 which has good generalization ability. To improve the generalization ability, we introduce the concept of Adaptive Similarity for grouping the training examples. Adaptive Similarity adapts the similarity measure on the course of training. The characteristics of SOLAR 2 are as follows: it learns extremely fast, constructs the network automatically, and it has no local minima problem.
    View full abstract
    Download PDF (622K)
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top