Wave-Nets: novel learning techniques, and the induction of physically interpretable models

Bhavik R. Bakshi; Alexandros Koulouris; George Stephanopoulos

doi:10.1117/12.170062

15 March 1994 Wave-Nets: novel learning techniques, and the induction of physically interpretable models

Bhavik R. Bakshi, Alexandros Koulouris, George Stephanopoulos

Proceedings Volume 2242, Wavelet Applications; (1994) https://doi.org/10.1117/12.170062
Event: SPIE's International Symposium on Optical Engineering and Photonics in Aerospace Sensing, 1994, Orlando, FL, United States

Abstract

A wavelet network, or Wave-Net is a connectionist network that combines the mathematical rigor and multiresolution character of wavelets with the adaptive learning of artificial neural networks. In this paper, we present some novel techniques for training and adaptation of Wave-Nets, and describe the induction of models that may be physically interpretable, and may provide useful insight into the system being modeled. Learning from empirical data is formulated as a constrained optimization problem. This formulation illustrates the complexity of the learning problem, and highlights the decision variables and the simplifying assumptions necessary for a practical learning methodology. Techniques for Wave-Net training and adaptation are developed for minimizing the L² or L^(infinity) norms. Minimizing the L^(infinity) norm is particularly relevant for solving control problems. The connection between Wave-Net parameters, and the error of approximation is derived using the principles of frame theory. The performance of Wave-Nets for different training methodologies, and basis functions is compared via case studies. Wave-Nets with Haar wavelets as activation functions are well-suited for problems where the output consists of a finite set of discrete values, as in classification problems. The mapping learned by Haar Wave-Nets may be represented as simple if-then rules, which provide an explicit and physically meaningful relationship between inputs and outputs. The relationship of learning by Haar Wave-Nets with other rule induction techniques, such as decision trees is explored.

Citation Download Citation

Bhavik R. Bakshi, Alexandros Koulouris, and George Stephanopoulos "Wave-Nets: novel learning techniques, and the induction of physically interpretable models", Proc. SPIE 2242, Wavelet Applications, (15 March 1994); https://doi.org/10.1117/12.170062

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available