Numerical Discrimination of the Generalisation Model from Learnt Weights in Neural Networks
Journal Title: Annals of Emerging Technologies in Computing - Year 2019, Vol 3, Issue 4
Abstract
This research demonstrates a method of discriminating the numerical relationships of neural network layer inputs to the layer outputs established from the learnt weights and biases of a neural network's generalisation model. It is demonstrated with a mathematical form of a neural network rather than an image, speech or textual translation application as this provides clarity in the understanding gained from the generalisation model. It is also reliant on the input format but that format is not unlike an image pixel input format and as such the research is applicable to other applications too. The research results have shown that weight and biases can be used to discriminate the mathematical relationships between inputs and make discriminations of what mathematical operators are used between them in the learnt generalisation model. This may be a step towards gaining definitions and understanding for intractable problems that a Neural Network has generalised in a solution. For validating them, or as a mechanism for creating a model used as an alternative to traditional approaches, but derived from a neural network approach as a development tool for solving those problems. The demonstrated method was optimised using learning rate and the number of nodes and in this example achieves a low loss at 7.6e-6, a low Mean Absolute Error at 1e-3 with a high accuracy score of 1.0. But during the experiments a sensitivity to the number of epochs and the use of the random shuffle was discovered, and a comparison with an alternative shuffle using a non-random reordering demonstrated a lower but comparable performance, and is a subject for further research but demonstrated in this "decomposition" class architecture.
Authors and Affiliations
Richard N M Rudd-Ortner, Lyudmilla Milhaylova
Keywords
Related Articles
- EP ID EP644856
- DOI 10.33166/AETiC.2019.04.001
- Views 79
- Downloads 0
Applications of Blockchain Technology beyond Cryptocurrency
Blockchain (BC), the technology behind the Bitcoin crypto-currency system, is considered to be both alluring and critical for ensuring enhanced security and (in some implementations, non-traceable) privacy for diverse ap...
Models of Research and the Dissemination of Research Results: the Influences of E-Science, Open Access and Social Networking
In contrast with practice in recent times past, computational and data intensive processes are increasingly driving collaborative research in science and technology. Large amounts of data are being generated in experimen...
Optimising Differentiated Services Strategies under IMS
The evolving standards of mobile communications, the wide variety of services they offer and the rapid growth of the Internet have made a merger of the two network technologies inevitable. One of the most prominent platf...
A Method of Body Parts Force Displacements Calculation of Metal-Cutting Machine Tools Using CAD and CAE Technologies
This paper describes a developed new method of body parts force displacements calculation of metal-cutting machine tools using combination of CAD and CAE technologies. It was carried out the analysis of analytical method...
Hardening CISCO Devices based on Cryptography and Security Protocols - Part One: Background Theory
Network Security is a vital part of any corporate and enterprise network. Network attacks greatly compromise not only the sensitive data of the consumers but also cause outages to these networks. Thus inadequately protec...