CN7023 Artificial Intelligence and Machine Vision Assignment - School Of Architecture, Computing, & Engineering, University of East London, UK
Task - Design, implement and report on neural network-based techniques for classification of a dataset of images.
Write a 3500 words research report, in the style of a research paper, including the following:
1. The research question(s) you are exploring and the experiments you designed to address these question(s).
2. A clear presentation of the methods (neural network implementation, network architectures, learning schedules, etc.) that were used, an outline of how they were implemented, and a discussion of why these methods were chosen.
3. A clear presentation of results, discussion and interpretation of results and conclusions.
NOTE: You can choose to complete the coursework using any one of the following approaches:
1. Mixture of image processing with artificial neural networks (with Matlab or Python)
2. Deep learning only (with Matlab or Python)
Research Report Format -
1. Title
2. Abstract
3. Introduction
Objective of the coursework (Research questions(s) you are exploring).
An overview of the coursework.
4. Methodology
Discussion of neural network classification for images
5. Simulations
Introduction of the dataset.
Input en coding / input representation (How and why?).
Procedures or how the implementation was carried out.
6. Results Obtained
Describe your results in the three different ways :
1. As a percentage (%), i.e. the test set achieved 95% accuracy.
2. Include an accuracy curve figure for the training, testing and validation results. The x-axis will represent the number of epochs and the y -axis will represent the percentage accuracy.
3. Include a confusion matrix figure as a visual representation of the accuracy you achieve.
7. Critical Analysis of results
Detailed analysis of the results.
8. Conclusions
Conclusions and comments
9. References and Formatting
10. Self -reflection discussion.
Attachment:- Artificial Intelligence & Machine Vision Assignment File.rar