Week 5: Practical Applications of Deep Learning
Practical Session
Overview
Present one of the papers below in 10–15 minutes. Explain the research in your own words for classmates who have not read the paper.
Your presentation should cover:
- Problem and motivation: What did the authors investigate, and why was it needed?
- Data and method: What data did they use, how does the method work, and what is new?
- Experiments and results: How was the method evaluated, and what do the main results show?
- Critical assessment: What are the strengths and limitations? What could be improved or tested next?
- Conclusion and critique: What are the main takeaways from the paper, and what is your own critical view of the work?
Use clear, readable slides, explain unfamiliar terms, cite your sources, and stay within the allotted time. Be ready to discuss your interpretation and answer questions.
Papers
| No. | Paper |
|---|---|
| 1 | TS2Vec: Towards Universal Representation of Time Series Yue et al. (2022), AAAI. |
| 2 | MOMENT: A Family of Open Time-series Foundation Models Goswami et al. (2024), ICML. |
| 3 | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer Shazeer et al. (2017), ICLR. |
| 4 | Federated Optimization in Heterogeneous Networks Li et al. (2020), MLSys. |
| 5 | Predicting Ship Main Engine Fuel Oil Consumption Using a Mixture of Experts Approach Ilias et al. (2026), IEEE Access. |
| 6 | Autoencoder based Anomaly Detection and Explained Fault Localization in Industrial Cooling Systems Holly et al. (2022), PHME. |
| 7 | Integrating Deep Learning Into Mechanical Engineering: A Systematic Review of Applications and Educational Implications Kollu and Kittur (2025), Computer Applications in Engineering Education. |