I'm a research scientist and algorithm engineer interested in machine perception, machine learning and artificial intelligence. I work with high-dimensional image and sound data and have been developing systems for image, speech and audio labeling, face recognition, multimedia content analysis and movie video summarization. At present, I am a research scientist at the McGovern Institute of Brain Research at MIT (Poggio Lab) and the Center for Brains, Minds and Machines (CBMM), where I am working on computational aspects of learning and intelligence, deep learning and representation learning for speech and image recognition. I am also affiliated with the lab for Computational and Statistical Learning (LCSL).
gevang [at] mit [dot] edu