Learning at Multiple Resolutions: Wavelets as Basis Functions in Artificial Neural Networks, and Inductive Decision Trees

Bakshi, Bhavik/ Koulouris, Alexandros/ Stephanopoulos, George/ Κουλούρης, Αλέξανδρος/ Στεφανόπουλος, Γεώργιος


Institution and School/Department of submitter: ΤΕΙ Θεσσαλονίκης
Issue Date: 1994
Publisher: Springer US
Citation: Wavelet Applications in Chemical Engineering, New York, 1994
Bakshi, B., Koulouris, A. & Stephanopoulos, G. (1994). Learning at Multiple Resolutions: Wavelets as Basis Functions in Artificial Neural Networks, and Inductive Decision Trees. Wavelet Applications in Chemical Engineering. 272:139-174.
Abstract: Learning at multiple resolutions provides a fast, hierarchical and efficient technique for extracting models from empirical data. In this chapter we describe the application of wavelets for multi-resolution learning in artificial neural networks and inductive decision trees, and show how wavelets may provide a unifying framework for various supervised learning techniques. A Wave-Net is an artificial neural network with activation functions derived from the class of wavelets. Wave- Nets combine the mathematically rigorous, multi-resolution character of wavelets with the adaptive learning of artificial neural networks. Learning with Wave-Nets is efficient, and is explicitly based on the local or global error of approximation. The advantages of Wave-Net learning over other artificial neural learning techniques are highlighted, and learning methods for minimizing the L2 or L∞ norms are described. The reduced black box character of Wave-Nets is demonstrated by the explicit relationship between Wave-Net parameters and the quality of learning, and by the ability to extract if-then rules from a Haar Wave-Net. The relationship between Haar Wave-Nets and other rule-extraction techniques such as decision trees is described.
Description: Δημοσιεύσεις μελών--ΣΤΕΤ-Δ--Τμήμα Τεχνολογίας Τροφίμων--1994
URI: http://195.251.240.227/jspui/handle/123456789/9985
ISBN: 978-1-4615-2708-4
978-0-7923-9461-7
ISSN: 0893-3405
Other Identifiers: http://link.springer.com/chapter/10.1007/978-1-4615-2708-4_5
Item type: other
Submission Date: 2018-02-28T16:08:57Z
Item language: el
Item access scheme: free
Institution and School/Department of submitter: ΤΕΙ Θεσσαλονίκης
Appears in Collections:Δημοσιεύσεις σε Περιοδικά

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



 Please use this identifier to cite or link to this item:
http://195.251.240.227/jspui/handle/123456789/9985
  This item is a favorite for 0 people.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.