The Department of Electrical Engineering at the Syed Babar Ali School of Science and Engineering (SBASSE) held a talk on ‘Exploring the computational principles of brain-wide development through deep learning’ on January 2, 2020. Dr. Asim Iqbal, Machine Learning Scientist at Google X, presented the talk.
Mapping the structure of the mammalian brain at cellular resolution is a challenging task and one that requires capturing key anatomical features at the appropriate level of analysis. Although neuroscientific methods have managed to provide significant insights at the micro and macro level, in order to obtain a whole-brain analysis at a cellular resolution requires a meso-scopic approach. In this regard, we introduce a novel approach to perform brain-wide analysis by developing deep neural network-based models that can explore the anatomical and functional principles in the mammalian brain. Furthermore, we decode the neural responses in mouse visual cortex through deep transfer learning to predict the presented stimuli with a high accuracy. This approach is going to be useful in developing biologically realistic deep neural networks for real world datasets.
As a Machine Learning Researcher at Google X, Dr. Iqbal works on the intersection of deep learning and computational neuroscience. With an undergraduate in Electrical Engineering, he studied Neural Systems and Computation at the Institute of Neuroinformatics, Department of IT and Electrical Engineering, ETH Zurich as a Master student and recently finished his PhD studies in Computational Neuroscience at UZH/ETH Zurich. During his graduate studies, Dr. Iqbal worked as a researcher in the field of machine intelligence at MIT, IBM Research, Allen Institute, UZH and ETH Zurich. His research work has been featured in Nature Machine Intelligence, Nature Methods and Nature Sci. Reports.
