[SOLVED] Marking criteria for COMP9444 Group Project R

Marking criteria for COMP9444 Group Project

Total marks for the project work: 30 marks.

1.   Project Notebook(s): 15 Marks

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

3.   Project Presentation: 10 Marks

Breakdown of marks for each component:

1. Marking criteria for Project notebook(s) [Total 15 marks]

Introduction, Motivation and/or Problem Statement (1 mark): Clearly define the problem statement or purpose of the project.

Data Sources or  RL Tasks  (1  mark): Data  sources  or  reinforcement  learning  tasks  are  clearly documented and described.

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 (3 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/State-of-the- art, where appropriate.

Discussion  (2   marks): Discuss  the  results  and  analysis,   provide  some   insight  about  system performance, including strengths, weaknesses, limitations and possible future work.

Writing (2 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 (2.5 marks)

Group-based

Clear problem statement (1 mark)

Clear presentation of data and data exploration or RL task (1 mark)

Clear presentation of models and/or methods (1 mark)

Clear presentation of results, result analysis or error analysis/qualitative examples (1 mark)

Quality of slides or visual presentation material (1 mark)