Computer vision researcher at MIT.
My previous work includes
Clustering by compression, where I applied computational tools approximating Kolmogorov complexity to the problem of clustering images of cosmological data for classification.
Semantic segmentation, where I developed a neural network architecture similar to that of U-Net to improve segmentation performance on thin objects and very large objects.
Indoor Localization, where I leveraged some machine learning techniques to enable indoor localization on mobile devices.