Location

La Jolla, CA

Start Date

1-1-1993 12:00 PM

Description

Artificial neural networks have been studied over a 30 year period and are a well developed computational technology applicable to a variety of difficult problems [1]. All neural networks are simulations of neurons and synapses based upon a primitive understanding of these biological structures. The distinctive feature of these networks is that they are trainable. By various iterative schemes, a set of well characterized data can be used to create a network which will produce a correct output function of an input vector. The learning is generalized, resulting in the ability to provide correct results for input vectors not contained in the training data. The term neural network has become nearly synonymous with a particular type: the feed-forward backpropagation neural network. We will use the term network in that sense here.

Book Title

Review of Progress in Quantitative Nondestructive Evaluation

Volume

12A

Chapter

Chapter 3: Interpretive Signal Processing and Image Analysis

Section

Neural Networks

Pages

783-788

DOI

10.1007/978-1-4615-2848-7_99

Language

en

File Format

application/pdf

Share

COinS
 
Jan 1st, 12:00 PM

Quantitative radioscopic profile analysis via neural networks

La Jolla, CA

Artificial neural networks have been studied over a 30 year period and are a well developed computational technology applicable to a variety of difficult problems [1]. All neural networks are simulations of neurons and synapses based upon a primitive understanding of these biological structures. The distinctive feature of these networks is that they are trainable. By various iterative schemes, a set of well characterized data can be used to create a network which will produce a correct output function of an input vector. The learning is generalized, resulting in the ability to provide correct results for input vectors not contained in the training data. The term neural network has become nearly synonymous with a particular type: the feed-forward backpropagation neural network. We will use the term network in that sense here.