SFU Machine Learning Reading Group

The goal of this reading group is to survey a variety of the current trends in the areas of machine learning and statistics. We will focus on topics that are not covered in the machine learning course, and that may be applicable in a wide variety of domains. The reading group should be viewed as complimentary to the course. We meet on Wednesdays at 1:30pm in room 9408, to join the mailing list please join the Google group.

Despite the name 'reading group', there is no reading requirement in order to attend. However, each week there will be a designated presenter and we expect everyone to act as a presenter for at most one session per semester. Each week the presenter will overview background on the topic and a motivating application, will describe at a high level the contribution of a recent paper in the area, and will discuss possible future directions.

October 22: Marginalized Stacked Denoising Autoencoders for Domain Adaptation (Bruce Krayenhoff)
October 29: A Provably Efficient Algorithm for Training Deep Networks (Mark Schmidt)
November 5: Multiple Kernel Learning (Hossein Hajimirsadeghi)
November 12: Sparse Coding (Brian Booth)
November 19: Gaussian Processes (Mark Schmidt)
November 26: Semi-Supervised Learning (Jasneet Sabharwal)
January 29: Multi-Task Learning (Ramtin Mehdizadeh Seraj)
February 5: Metric Learning (Bruce Krayenhoff)
February 19: Structured Prediction (Arash Vahdat) (References: 1, 2, 3, 4)
March 5: Particle Filtering (Brian Booth) (Video)
March 12: Duality and Alternating Direction Method of Multipliers (Mengliu Zhao) (References: 1, 2)
March 19: Structured Sparsity (Nataliya Shapalova) (Other Slides)
April 23: Feature Hashing Trick (Jasneet Sabharwal)

Ramtin's map of machine learning

Mark Schmidt > SFU Machine Learning Reading Group