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|
|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|
|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:This item is a favorite for 0 people.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.