Filter by keyword, subject, or both. Updates live as new model answers are added to our portal.
Data Science / Artificial Intelligence / Generative Modelling
Generative Modelling Case Study: GANs for Medical Imaging, Cybersecurity and Creative AI
This Generative Modelling Case Study requires students to design, implement and evaluate Generative Adversarial Networks (GANs) across a range of synthetic and real-world applications. The coursework develops both theoretical understanding and practical deep-learning skills, with emphasis on building models, evaluating generated data and critically interpreting model performance. The assessment addresses research understanding, originality, future development and scholarly communication in data science. Generative modelling case study… Part 1 – Building and Understanding GANs from Scratch focuses on fundamental GAN concepts using synthetic two-dimensional data. Students first reproduce a sine-wave GAN from the tutorial and then create a second synthetic distribution using either a 2D spiral, a mixture of Gaussians or a noisy parametric curve. They must modify aspects of the GAN architecture, such as activation functions or network depth, and visually compare generated samples with the original data distribution. Generative modelling case study… Part 2 – Real-World GAN Applications extends the work across three application domains. The first application uses the BloodMNIST subset of MedMNIST to train a DCGAN that generates synthetic blood-cell microscope images. Students explore the dataset, analyse class distributions, train the model, monitor generator and discriminator losses and compare real and generated images using both visual inspection and quantitative measures such as the Fréchet Inception Distance (FID). An optional extension involves implementing a class-conditioned GAN capable of generating images from specific categories. Generative modelling case study… The second application addresses cybersecurity using the CICIDS 2017 intrusion-detection dataset. Students construct a GAN that generates synthetic network-traffic feature vectors rather than images. The model is trained using benign and denial-of-service traffic, and generated samples are compared with real traffic using dimensionality-reduction techniques such as PCA or t-SNE. Students must evaluate how closely the synthetic traffic reflects the distribution of genuine network data. An extension allows analysis of the full CICIDS dataset and evaluation across different attack types. Generative modelling case study… The third application explores Creative AI using the Google QuickDraw pizza category. Students implement another DCGAN to generate artificial pizza sketches, track training behaviour across epochs, and compare generated sketches with genuine examples using both visual inspection and quantitative metrics such as FID. Extension work may examine additional QuickDraw categories and investigate how model performance changes with class and sketch complexity. Generative modelling case study… Submission consists of a 6–8 page report together with working code. The report should explain the analysis undertaken, justify modelling decisions, describe the network architectures, interpret the results and incorporate suitable figures, evaluation metrics and references. The accompanying code must reproduce the figures, models and numerical results reported and must execute successfully when tested. Generative modelling case study… The marking scheme places 60% of the marks on code and 40% on the report. Within the coding component, 40 marks relate to completing the GAN modelling tasks and 20 marks assess code quality, modularity and annotation. The report is assessed on discussion and interpretation of the analysis, justification of architectural choices, results presentation, document quality, figures and appropriate academic references. Generative modelling case study… Important for the public Reference Library: the brief explicitly states that students must not use generative AI to write the report, and the rubric states that AI-generated report text can result in zero marks for the whole assignment. Therefore, use this entry only as a high-level public description of the assessment and do not present generated report content as something students can submit directly. Generative modelling case study… Generative modelling case study…
Read Model Answer →
Artificial Intelligence / Machine Vision / Computer Vision
Artificial Intelligence and Machine Vision: Neural Network-Based Image Processing Application
This postgraduate Artificial Intelligence and Machine Vision coursework requires students to design, implement and critically evaluate a neural network-based image-processing application addressing a real-world problem. Students may select an application such as medical imaging, plant or fruit classification, skin cancer detection, object detection or image segmentation and must demonstrate an appropriate end-to-end machine vision workflow. CN7023 Coursework T2 25-26 (1) The project begins with a clear definition of the selected real-world problem, the objectives of the proposed solution and its potential practical impact. Students are expected to demonstrate creativity in selecting and designing their approach, explain the neural-network or image-processing methods adopted and justify why the selected techniques are suitable for the chosen dataset and application. CN7023 Coursework T2 25-26 (1) A substantial component focuses on simulation and implementation. Students describe the dataset, including its source, size, classes and representative images, before explaining how image data were encoded and preprocessed for use within the chosen neural network. The report must then document the selected network architecture, learning algorithm and procedures used for training, validation and testing. CN7023 Coursework T2 25-26 (1) Model performance must be communicated using quantitative and visual evidence. Required outputs include test-set accuracy, accuracy curves across training, validation and testing, and a confusion matrix supported by appropriate explanation. Students must also critically analyse the results, identify factors affecting model performance and discuss alternative methods or simulation changes that could improve the solution. CN7023 Coursework T2 25-26 (1) The coursework permits several technical routes, including combining image processing with artificial neural networks, deep learning or computer vision, or focusing on one of these approaches independently. Development may be completed using MATLAB or Python. The wider module covers artificial neural networks, CNNs, digital image processing, image restoration, compression, segmentation, classification and ethical, legal, privacy and social issues associated with AI systems. CN7023 Coursework T2 25-26 (1) Module handbook 2526-B (1) Overview word count: approximately 335 words. Important note: the coursework cover page labels the assignment as “Individual Assignment 100%,” but the module handbook clarifies that the coursework report itself contributes 50% of the module, with the remaining marks allocated to MATLAB course completion (20%), lab tasks (15%) and presentation (15%). For the Reference Library, I would use the handbook’s 50% report weighting if you need to record the assessment contribution.
Read Model Answer →
Network Security
1,500 words
The Case Study – Network Security Planning and Upgrade
This individual assessment for the Network Security module requires students to work as network consultants and carry out network and security planning and an upgrade for an imaginary company. The assignment is titled “The Case study” and requires students to produce a written report presenting solutions to the problems identified within the case study. The assessment is worth 15 credits and requires approximately 1,500 words, with a permitted variation of ±10%. The coursework focuses on applying network security concepts and protocols to contemporary Internet and mobile-based solutions and technologies. Students are expected to analyse the requirements of the imaginary organisation, identify relevant network and security issues and propose appropriate planning and upgrade solutions. The report should demonstrate an understanding of network security technologies while considering the organisation's information assets and operational requirements. A significant part of the assessment concerns network performance. Students must provide recommendations and suggestions for addressing network performance issues identified in the case study. Where the proposed solution changes the existing network design, an appropriate network diagram should be included. The brief allows students to use tools such as Packet Tracer or other suitable applications to represent the proposed network design. The assignment also requires students to consider security policy and network protection. The existing security policy should be reviewed and recommendations should be made for improving it. Students are specifically instructed not to create a completely new security policy because the organisation already has one. In addition, the report should discuss how appropriate security measures could be implemented across the network. Detailed device configurations are not required, although relevant examples or configuration snippets are encouraged. Because the information provided in the case study is incomplete, students must identify and document their assumptions and requirements. This includes defining unspecified parameters such as network speeds, device features and existing policy details. The assumptions and requirements section is therefore an important part of the investigation and contributes to the assessment mark. The final report should summarise the key findings of the investigation and may recommend how any remaining IT support budget could be used. References must be included and used effectively to support the discussion. The marking criteria allocate 10% to the introduction, 10% to assumptions and requirements, 20% to improving performance, 20% to policy amendments, 20% to securing the network, 10% to the conclusion/summary and 10% to references. The assessed learning outcomes cover the application of network security concepts and protocols, critical evaluation and design of security policies, understanding of IT governance and its influence on organisational security policy, and critical review of current research and technological advances in network security. The brief also permits AI assistance, but any AI tools used must be referenced and their use summarised at the end of the report before the reference list.
Read Model Answer →
Network Security and Incident Report
1,500 words
Network Security and Incident Report – Megadodo Publications
This 1,500-word individual coursework for the Network Security and Incident Report module examines the network infrastructure and security challenges of Megadodo Publications, a company located near Warwick that has expanded into two buildings, Ursa Major Alpha and Ursa Minor Beta. Despite investment in new networking equipment, the organisation is experiencing poor network performance and repeated security incidents involving the leakage of sensitive information into the public domain. The situation is particularly urgent because the company is negotiating an important government contract. The student is placed in the role of a network security professional asked to investigate the existing environment and provide recommendations for improving its infrastructure and security. The case study provides a network topology, addressing scheme, equipment information and an existing security policy. The network connects departments across the two buildings and includes servers, management systems, sales, marketing, legal, finance, software development, product testing, administration, IT support, Wi-Fi and a rented floor occupied by a separate start-up company. The addressing scheme identifies separate subnets for several organisational functions, while the topology includes multiple switches, routers, servers and wireless access points. The report requires students to make reasonable assumptions where information is incomplete and document those assumptions at the beginning of the report. The first substantive task evaluates how the organisation's network performance could be improved. Recommendations should address the existing infrastructure and, where the design is changed, include an appropriate network diagram using tools such as Packet Tracer or other suitable applications. The second major area addresses amendments to the existing security policy. Students should recommend improvements to the current policy rather than create a completely new policy. The report must also discuss how appropriate security measures could be implemented across the network and its devices. Detailed device configurations are not required, although relevant examples or configuration snippets are encouraged. The final section requires a summary of the key findings and recommendations, together with a proposal for how the organisation could use its remaining IT support budget of approximately £8,000 and identify areas for future investment. The assessment is divided into introduction, assumptions and requirements, improving performance, policy amendments, security and devices, summary and budget, and references. The marking scheme allocates 50% of the module mark to this coursework, with the individual report submitted as a single DOC, DOCX or PDF document.
Read Model Answer →