Python users group in Knoxville, TN
This month we have two short presentations about neuromorphic computing systems. See below for more details about each talk.
Katie Schuman of ORNL will give a presentation titled "Evolutionary Optimization for Neuromorphic Systems". In this talk, a brief introduction to neuromorphic or brain-inspired computing systems will be given, including the motivation for neuromorphic computing systems, as well as challenges associated with programming and utilizing them for real-world applications. We will present a training algorithm for neuromorphic systems called Evolutionary Optimization for Neuromorphic Systems, which has been used to train "programs" for neuromorphic systems that perform tasks such as data classification and autonomous robot control.
Jim Plank of UTK will talk about the "TENNLab Open-Source Neuromorphic Exploratorium". Over the past five years, the TENNLab group, which is a collaboration between researchers at the University of Tennessee and Oak Ridge National Laboratory, has been developing software to drive spiking Neuromorphic computing systems. This includes multiple simulators of spiking neuromorphic devices, applications to utilize them, machine learning solutions to “program” them, and all of the glue in between. The latest revision of the Exploratorium has been designed specifically to leverage the vast variety of machine learning environments available via Python. This talk will provide an overview of the framework, detail the software architecture and how it leverages work in the field, and show some demonstrations of results.