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 84
- Downloads 0
Numerical Discrimination of the Generalisation Model from Learnt Weights in Neural Networks
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 mo...
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...
Stereoscopic Human Detection in a Natural Environment
The algorithm presented in this paper is designed to detect people in real-time from 3D footage for use in Augmented Reality applications. Techniques are discussed that hold potential for a detection system when combined...
Comparing the Complexity of Two Network Architectures
A Service Provider has different methods to provide a VPN service to its customers. But which method is the least complex to implement? In this paper, two architectures are described and analysed. Based on the analyses,...
A Novel Approach for Network Attack Classification Based on Sequential Questions
With the development of incipient technologies, user devices becoming more exposed and ill-used by foes. In upcoming decades, traditional security measures will not be sufficient enough to handle this huge threat towards...