This assignment focuses on applying machine learning techniques to analyse and make predictions based on a given dataset representing a real-world scenario. Students will perform data exploration, preprocessing, model selection, training, evaluation, and interpretation, assessing the performance of their chosen models and drawing meaningful conclusions from the results. The submission comprises three components, including a written report detailing the methodology and findings, a reflection discussing challenges and learning experiences, and the Python code written for the analysis. 

The marking criteria are divided into three main areas. Data Preprocessing & Exploration (25%) evaluates how well the dataset is handled, including feature analysis and preprocessing steps. Model Development & Evaluation (40%) focuses on selecting and training the machine learning models, comparing the performance, and interpreting the results. Report Quality (25%) looks at how well the report is structured, the clarity of explanations, and the use of visuals and supporting evidence. Reflection (10%) assesses the depth of insights gained from the process and how challenges were addressed. 

This assignment focuses on solving an optimisation problem using search strategies to find an efficient solution in a real-world scenario. Students will model the problem, implement the selected algorithm, assess its performance, and analyse the results. The assignment involves problem formulation, algorithm design, implementation, testing, and analysis to evaluate the effectiveness of the solution. The submission comprises three components, including a written report detailing the algorithm and findings, a reflection discussing challenges and learning experiences, and the Python code written for the solution. 

The marking criteria are divided into four areas. Modelling and Algorithm Design (25%) assesses how well the problem is formulated, including data structure choices and the design of the selected search algorithm. Implementation (40%) evaluates the correctness and efficiency of the implemented algorithm. Testing and Analysis (20%) focuses on running the implemented algorithm, capturing results, and analysing its performance based on relevant metrics. Reflection (15%) considers insights gained, challenges faced, and potential improvements.

This assignment focuses on applying deep learning techniques to solve a real-world problem. Students will preprocess a dataset, modify pre-trained models, train and evaluate their performance, and analyse the results. The assignment emphasises model selection, data handling, training process design, and performance interpretation to assess how well different approaches work for the given task. This is a group assignment (2-3 students) with a written report covering the methodology, results, and analysis. Additionally, each student submits an individual reflection discussing their contributions, challenges faced, and lessons learned.

The marking criteria are divided into five main areas. Data Preparation and Preprocessing (15%) assesses the quality of data handling, including preprocessing steps and code clarity. Model Selection and Modification (28%) evaluates the choice of pre-trained models and how they are adapted for the task. Model Training and Evaluation (22%) focuses on the training process, performance metrics, and interpretation of results. Written Report (20%) is graded based on organisation, clarity, content depth, and use of visualisations. Reflection (15%) is an individual component assessing insights gained, challenges faced, and contributions to the group work.