Computer vision researcher at MIT.

My previous work includes

• Visual Reasoning, where I applied modular neural networks to achieve state-of-the-art accuracy on the CLEVR dataset, while providing interpretable model outputs.

• 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.

• The Mahali Space Weater Monitoring Project, where I developed a mobile application and scientific computing framework to enable real-time data processing and collection on mobile devices.

• Indoor Localization, where I leveraged some machine learning techniques to enable indoor localization on mobile devices.

• Automated NMR assignment, where I applied machine learning techniques to reduce the search space of an algorithm for automatically assigning backbone protein sequences. Read the paper