PHY 4905 "Machine Learning"
Spring 2021
 
Project Assignments

Rubric (40 pts total):

• Introducing the topic [10]: what is the question we are trying to answer? Why is it important? Previous approaches - pros and cons. Why do we expect a (new) ML method would help in this case?
• Machine learning aspect [10]: what ML technique was applied, what dictated the choice of this particular technique, rough description of the technique, choice of hyperparameters, training/validation (if applicable), results, conclusions.
• Overall impression [5] and time management [5]: optimal mix of text/graphics/formulas, no spelling and grammar mistakes, appropriate font size, labelling the plots/axes, effective use of color/illustrations; finish within the alloted time of 12 min. (leaving 3 min for questions).
• Feedback [10]. The remaining 10 pts will be distributed for submitting an evaluation and feedback for at least ten presentations.

Below are some topics which we did not get a chance to mention or discuss in detail in class. They are all implemented in scikit-learn and make for suitabe final projects. You will need to briefly explain the basic idea, show some simple example as an illustration of a typical implementation, and present a performance comparison against a competitor method.

• Novelty and outlier detection.
• Ensemble methods (two topics):
  • Adaboost
  • VotingClassifier and VotingRegressor
• Decomposing signals in components (any one method)
• Manifold learning (any one of the 8 methods)
• Clustering
• Hierarchical clustering
• Affinity propagation
• Clustering performance evaluation
• Autoencoders
• Restricted Boltzmann machines