Marking criteria for COMP9444 projectSPSS

Java Python Marking criteria for COMP9444 project

Total marks for the project work: 35 marks.

1.   Project Notebook(s): 20 Marks

2.   Summary Report (max 4 pages): 5 marks

3.   Project Presentation: 10 Marks

Breakdown of marks for each component:

1. Marking criteria for Project notebook(s) [Total 20 marks]

Introduction, Motivation and/or Problem Statement (2 marks): Clearly define the problem statement or purpose of the project.

Data Sources or RL Tasks (2 marks): Data sources or reinforcement learning tasks are clearly documented and described. Enough detail is provided for the data to be found again.

Exploratory Analysis of Data or RL Tasks (3 marks): Provide details about the properties, number of classes, pre-processing, challenging aspects, etc. of the data (or the RL task).

Models and/or Methods (4 marks): Model(s) and/or Method(s) are judiciously chosen and appropriately

applied. If building on previous work, identify the source and clearly delineate which parts are your own work.

Results (3 marks): Results are clearly shown, discussed, evaluated using appropriate metrics. Good use of   graphs or other visualizations, where possible. Comparison with previous methods/SOTA, where appropriate.

Discussion (3 marks): Discuss the results and analysis, provide some insight about system performance, including strengths, weaknesses, limitations and possible future work.

Marking criteria for COMP9444 projectSPSS Writing (3 marks): Notebook(s) are presented in a readable format, appropriate section/subsection headings are provided in markdown format, codebase is easy to follow.

2. Marking criteria for Project Summary Report [Total 5 marks]

Introduction (0.5 mark): Provide a high-level description of the project.

Literature Review (0.5 mark): Review existing methods/techniques relevant to the project.

Models and/or Methods (0.5 mark): Justify and explain the selection of models and/or methods appropriate to the task.

Experimental Setup (0. 5 mark): Provide clear details about model parameters, evaluation metrics to be used, data split into training, validation, and testing, etc.

Results (0.5 mark): Discuss the main findings and results. How well does the system perform? Compare to other method(s)/SOTA, if possible.

Conclusions (0.5 mark): What are the key strengths and weaknesses of the proposed solution? What are the key limitation(s)? Recommendations for future work.

Details in the report (1 mark): Report provide sufficient details to understand the project clearly - motivation, dataset, rationale for the selection of models, results, and conclusions.

Overall quality of the report (1 mark): Summary Report is well-presented and formatted, within specified length, without grammatical mistakes or typos.

3. Marking criteria for Project Presentation [Total 10 marks]

Individual-based

Contribution to the presentation (2.5 marks)

Clearly spoken and understandable (2