I met with Professor Verma this week to discuss the MMC implementation, which I was able to complete with a soft constraint on the distances between dissimilar data points. Separately, we reviewed two papers on few-shot learning and delved into concepts such as Bregman divergences, Polya-Gamma augmentation and one-vs-each approximation to softmax, which I will further investigate for my own edification.

For this coming week, I plan to incorporate the structural integrity score into my MMC model to complete the Structure Preserving Metric Learning algorithm.