Projects
A project consists of a report and a presentation. Report should be about 5 pages and has to contain following sections:
- Introduction - description of the task and why it is important,
- Background - briefly mention previous work or classical methods usually applied to the task,
- Dataset - describe the dataset you used - how many samples, how many features, how did you collect it etc.,
- Method - describe the method you used - what kind of network was used, how many layers, how many nodes etc.,
- Results - provide the training plots and resulting tables,
- Discussion - brief analysis of the results - in what cases it worked when not,
- Future work - provide some ideas how to improve the results or for further experiments,
- Conclusion - summarize the report in one paragraph.
Presentation should be 10 minutes + 5 minutes for questions.
Presentations will be held on Monday 25th of January 2016 at 12 in J. Liivi 2-512 (the usual class time). Deadline for submitting the reports is Friday 29th of January 2016.
Final projects:
- "Generating texts in Estonian language" - Robert Roosalu (slides) (report)
- "Sentiment classification" - Aqeel Labash (slides) (report)
Other interesting works: