Each presentation must be developed by teams of three students. Exceptions may be granted with written permission from instructor (via Ed). The goal of each team member is to become an expert in one of the following topics and jointly prepare a presentation for the class. According to the dates below, a maximum of 25 minutes will be given to students for their presentations. The deliverable is a set of slides in PDF format related to the topic of your choice.
Each team must collect feedback and get approval from the instructor at least four days before the presentation. Please upload your presentation to Gradescope in advance and let your instructor know about it.
|Maximum Likelihood Estimation (MLE)||Dec 6||Salam, Jessica, Joori|
|Maximum A Posteriori Estimation (MAP)||Dec 6||Reilly, Billy, Abby|
|Collaborative Filtering||Dec 6||Jake, Mehrsa, Tim|
|K-Means ++||Dec 8||Victoria, Jason, Nathan|
|Gaussian Mixture Models||Dec 8||Nayan, CJ, Danny|
|Gradient Boosting||Dec 8||James, Ryan, Robert|
|Pytorch (crash course)||Dec 8||Jack, Liz, Shawn|
|Tensorflow/Keras (crash course)||Dec 8||Arlen, Sandra, Caroline|
|Hidden Markov Models||Dec 8||Thibaut|
|Convolutional Neural Networks||Dec 13||Patrick, Jordan, Justin|
|Autoencoders||Dec 13||Osama, Sedat, Riley|
|Long Short-Term Memory Networks||Dec 13||Anakin, Tony|
|Generative Adversarial Networks||Dec 13||Masoud, Maryam, Lily|
|Word Embeddings / Word2Vec||Dec 13||Christopher|
|Deep Reinforcement Learning||Dec 13||Alfred, Brennan, Ray|
On the day of your presentation, the instructor will be observing and assessing the following items.
- Introduction provides context and lays out the topic nicely [15 pt]
- Appropriate amount of material is well-communicated within the allotted time [20 pt]
- Team appears well-prepared, mastering the assigned subject [30 pt]
- Slides are well-organized, and visual aids are used appropriately [20 pt]
- Team answers questions correctly [15 pt]