Differences
This shows you the differences between two versions of the page.
|
dsm:assignments:01 [2026/06/10 19:51] emilian.radoi |
dsm:assignments:01 [2026/10/04 16:41] (current) emilian.radoi |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| ===== Project ===== | ===== Project ===== | ||
| - | <hidden> | ||
| * **Team**: 2 members. | * **Team**: 2 members. | ||
| * **Project Selection**: | * **Project Selection**: | ||
| Line 19: | Line 18: | ||
| === Milestones and Deliverables === | === Milestones and Deliverables === | ||
| - | == 1. M1 (03.11.25) - Related Work / State-of-the-Art Review + Presentation (1p) == | + | == 1. M1 (02.11.25) - Related Work / State-of-the-Art Review + Presentation (1.5p) == |
| * **Objective**: Establish the research context by reviewing and summarising related work (existing studies and relevant literature related to your topic). | * **Objective**: Establish the research context by reviewing and summarising related work (existing studies and relevant literature related to your topic). | ||
| * **Action Items**: | * **Action Items**: | ||
| Line 27: | Line 26: | ||
| * **Documentation (English, IEEE format)**: Create a report section (2 pages excluding references) detailing your findings, including citations of key papers and a discussion of how your project will build upon or differ from existing work. | * **Documentation (English, IEEE format)**: Create a report section (2 pages excluding references) detailing your findings, including citations of key papers and a discussion of how your project will build upon or differ from existing work. | ||
| * **Grading** | * **Grading** | ||
| - | * **(0.3p) References**: Include a minimum of 10 academic papers in your review. | + | * **References**: Include a minimum of 10 academic papers in your review. |
| - | * **(0.2p) Research Questions**: Provide at least 2 meaningful research questions that will answer, or that should be addressed in future work. Helpful guide [[https://atlasti.com/guides/qualitative-research-guide-part-1/research-question | here]]. | + | * **Research Questions**: Provide at least 2 meaningful research questions that you will answer, or that should be addressed in future work. Helpful guide [[https://atlasti.com/guides/qualitative-research-guide-part-1/research-question | here]]. |
| - | * **(0.5p) Content**: Capture the current landscape of the topic. You may use qualitative surveys for inspiration. Also **check the tips below**). In your review explicitly answer these sub-questions, each worth 0.1p: | + | * **Content**: Capture the current landscape of the topic. You may use qualitative surveys for inspiration. Also **check the tips below**). In your review explicitly answer these sub-questions, each worth 0.1p: |
| - | * What datasets are used and why? (0.1p) | + | * What datasets are used and why? |
| - | * What benchmarks or evaluation methods are used? Are there any limitations? (0.1p) | + | * What benchmarks or evaluation methods are used? Are there any limitations? |
| - | * What are the current shortcomings in the field? (0.1p) | + | * What are the current shortcomings in the field? |
| - | * How do the works relate to each other? (e.g: one paper addresses another's limitations, several share the same assumptions or techniques)? (0.1p) | + | * How do the works relate to each other? (e.g: one paper addresses another's limitations, several share the same assumptions or techniques)? |
| - | * What architectures and training techniques are used? Any noteworthy or novel approaches? (0.1p) | + | * What architectures and training techniques are used? Any noteworthy or novel approaches? |
| * **Presentation**: | * **Presentation**: | ||
| * Prepare a 5 minute presentation (with slides) that summarises your review. | * Prepare a 5 minute presentation (with slides) that summarises your review. | ||
| * State the topic / problem, the context, and the direction you intend to pursue (your research questions). | * State the topic / problem, the context, and the direction you intend to pursue (your research questions). | ||
| - | * The presentation is graded on a 0 to 1 scale and will be used to scale the M1 score. | + | * Your M1 score will be determined based on the presentation. Both team members must contribute to the presentation. |
| * **Tips**: | * **Tips**: | ||
| * How to read research papers efficiently - [[https://dslsrv1.rnet.missouri.edu/resources/HowToReadAPaper.pdf | the 3-pass method]]. | * How to read research papers efficiently - [[https://dslsrv1.rnet.missouri.edu/resources/HowToReadAPaper.pdf | the 3-pass method]]. | ||
| Line 52: | Line 51: | ||
| | | ||
| - | == 2. M2 (28.11.25) - Dataset Collection and Baseline Results (1p) == | + | == 2. M2 (27.11.25) - Dataset Collection and Baseline Results (0.5p) == |
| * **Objective**: Obtain the datasets required for your project and implement a baseline model for comparison. | * **Objective**: Obtain the datasets required for your project and implement a baseline model for comparison. | ||
| * **Action Items**: | * **Action Items**: | ||
| Line 71: | Line 70: | ||
| - | == 3. M3 (19.12.25) - Own Contribution (1p) == | + | == 3. M3 (18.12.25) - Own Contribution (0.5p) == |
| * **Objective**: Develop and implement your original contribution to the field, either by addressing a new research problem or improving an existing approach. | * **Objective**: Develop and implement your original contribution to the field, either by addressing a new research problem or improving an existing approach. | ||
| * **Types of contributions**: | * **Types of contributions**: | ||
| Line 90: | Line 89: | ||
| - | == 4. M4 (12.01.25) - Final paper + Presentation (1p) == | + | == 4. M4 (11.01.25) - Final paper + Presentation (1.5p) == |
| * **Objective**: Compile your project into a well-organised academic report. | * **Objective**: Compile your project into a well-organised academic report. | ||
| * **Action Items**: | * **Action Items**: | ||
| Line 110: | Line 109: | ||
| * Conclusions and potential areas for future research. | * Conclusions and potential areas for future research. | ||
| * **Presentations tips**: create well-polished slides with clear visuals, including figures, graphs and performance metrics. | * **Presentations tips**: create well-polished slides with clear visuals, including figures, graphs and performance metrics. | ||
| - | * **Evaluation**: The presentation will be graded based on clarity, depth of explanation, the quality of results and the Q&A section. The final project grade will be weighted based on the presentation quality. | + | * **Evaluation**: The presentation will be graded based on clarity, depth of explanation, the quality of results and the Q&A section. The M4 grade is determined based on the presentation quality. Both team members must contribute to the presentation. |
| * **Upload M4 (Documentation and Slides)**: [[https://curs.upb.ro/2025/mod/assign/view.php?id=24456|Upload]] must contain title and authors. | * **Upload M4 (Documentation and Slides)**: [[https://curs.upb.ro/2025/mod/assign/view.php?id=24456|Upload]] must contain title and authors. | ||
| Line 118: | Line 117: | ||
| ==== Grading System ==== | ==== Grading System ==== | ||
| * **Total Points** = M1 + M2 + M3 + M4 | * **Total Points** = M1 + M2 + M3 + M4 | ||
| - | * M1 and M4 will have their grade (G) scaled by the score of the presentation (P): TOTAL = G * P | ||
| ---- | ---- | ||
| Line 173: | Line 171: | ||
| * **Error analysis on the baseline**: You can analyse the errors made by your baseline and try to propose targeted solutions. In this case, the baseline should be a well performing model from the related work, not a simple finetuned architecture. | * **Error analysis on the baseline**: You can analyse the errors made by your baseline and try to propose targeted solutions. In this case, the baseline should be a well performing model from the related work, not a simple finetuned architecture. | ||
| - | </hidden> | + | |
