Abstract
The large-scale reconstruction of synaptic-level wiring diagrams remains an attractive target for achieving greater understanding of nervous systems in health and disease. Progress has been severely limited due to technical issues involved in the imaging and analysis of nanometer-resolution brain imaging data. In this talk, we will discuss recent advances in using deep learning techniques (e.g., recurrent neural networks) and very large scale computation and storage capabilities in order to drive order-of-magnitude progress in automated analysis of 3d electron microscopy data. We will also discuss some of the biology that these projects are enabling, and prospects for making these tools and techniques widely available to neuroinformatics researchers.