Research: All

What makes ImageNet good for Transfer Learning?

This work provides an empirical investigation into the various facets of this question, such as looking at the importance of the amount of examples, number of classes, balance between images-per-class and classes, and the role of fine and coarse grained recognition. We pre-train CNN features on various subsets of the ImageNet dataset and evaluate transfer performance on a variety of standard vision tasks.

Virtual steerable acousto-optic waveguides for non-invasive deep brain imaging and stimulation

We introduce a radical approach to use ultrasonic waves to confine and steer light deep (a few millimeters) into the tissue without having to insert a physical light guide. Ultrasonic pressure waves launched from outside can propagate in the brain tissue with minimal loss and change the density of medium locally and interact with light to define and steer the trajectory of light.