Towards Robust and Energy-Efficient Spike Based Machine Intelligence
Today, deep learning has empowered the digital age, enabling ‘intelligence’ in almost all technology that surrounds us. However, the cost associated in terms of computing resources and energy consumption is very high. We need something with the potential of empowering low-power machine intelligence through sparse, event-driven computations. Enter Spiking Neural Networks (SNNs): often referred to as the third generation of neural networks (or Neuromorphic Computing), there are no current learning or inference techniques that are capable of harnessing the benefits of SNNs.
“In this talk, I will present an overview of the recent efforts in SNNs, in both algorithm and hardware (time permitting), addressing the limitations and advantages of spike-driven learning and computations.”
h3 style=”text-align: justify;”>Dr. Priyadarshini Panda
is an assistant professor in the electrical engineering department at Yale University, USA.
She is the recipient of the 2019 Amazon Research Award, that funds research in areas of machine learning, robotics and operations research.
Her research interests include neuromorphic computing and deploying robust and energy efficient machine intelligence.
