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 86
- Downloads 0
Cross-cultural Usability Issues in E/M-Learning
This paper gives an overview of electronic learning (E-Learning) and mobile learning (M-Learning) adoption and diffusion trends, as well as their particular traits, characteristics and issues, especially in terms of cros...
Design and Implementation of a Long Range Indoor VLC System using PWM
Visible Light Communications (VLC) is currently considered one of the most promising Optical Wireless Communications (OWC) for commercial applications, due to the widespread deployment of Light Emitting Diodes (LEDs) for...
E-mobile Acceptance Using Unified Theory of Acceptance and Use of Technology (UTAUT): Research on Universities in Jordan
An investigation into the variables that have a bearing on the acceptance of D-learning (Digital-learning) services such as E-learning and M-learning, in Jordanian universities is presented. This is followed with a discu...
Hardware Dynamic Memory Manager for Hard Real-Time Systems
This paper presents novel hardware architecture of dynamic memory manager providing memory allocation and deallocation operations that are suitable for hard real-time and safety-critical systems due to very high determin...
Object Identification Based on the Automated Extraction of Spatial Semantics from Web3D Scenes
We present a web-based methodology for the extraction of semantic information and object identification in poorly annotated Web3D scenes. Our approach is based on a set of rules that mimic human spatial cognition, backed...