UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Neural network programming and portability

Bavan, Arumugam Siri; (1991) Neural network programming and portability. Doctoral thesis (Ph.D), UCL (University College London). Green open access

[img] Text
Neural_network_programming_and.pdf

Download (5MB)

Abstract

Artificial neural networks, inspired by the neural structure of the brain, is a rapidly expanding field of research based on algorithms to solve a wide spectrum of tasks including speech recognition, image processing, planning, optimisation and other pattern processing tasks. Although a growing number of neural models have been developed to support a variety of applications, neural network programming is still mainly done using conventional languages. This thesis investigates the problems concerned with the programming of neural network models and their portability. The main goal of this thesis is to propose and develop a programming system that can facilitate the implementation of a range of neural network models on a range of hardware. This led to the design and implementation of a programming system called NPS, and a specialised neural network implementation language called NIL. NIL, which forms the neucleus of the programming system NPS, is a low level, machine independent network specification language designed to map a spectrum of neural models onto a range of architectures and thus supporting portability. The neural network programming system NPS provides the user with a system consisting of: 1. A programming language, NIL, to specify network models. 2. A utility, to save partially trained networks for further training. 3. Libraries of functions and algorithms, to aid the network construction and the execution of standard models. The neural network programming language NIL consists of two major components: 1. A network implementation sub-language, which provides mechanisms for specifying the functions of the nodes and the interconnection topology of the network. 2. A manipulation sub-language, which provides interactive control and modification facilities for use during the training and the recall phase of the network. These sub-languages together produce a low level, machine independent network specification language that can be used to port neural network models. Chapter 1 introduces the thesis and the background concepts, namely, neural networks, and programming systems for neural networks. In chapter 2, a survey of neural network programming systems is presented. In chapter 3, the proposed NPS programming system is presented. In chapter 4, a detailed description of the NIL language is presented. In chapter 5, implementation details of the NPS and NIL is presented. In chapter 6, an assessment of NPS and NIL is presented. Finally in chapter 7, conclusions are drawn and future work is discussed.

Type: Thesis (Doctoral)
Qualification: Ph.D
Title: Neural network programming and portability
Open access status: An open access version is available from UCL Discovery
Language: English
Additional information: Thesis digitised by ProQuest.
Keywords: Applied sciences; Artificial neural networks
URI: https://discovery.ucl.ac.uk/id/eprint/10107664
Downloads since deposit
14Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item