Lightning Talk: A Perspective on Neuromorphic Computing.

Neuromorphic computing, based on Spiking Neural Networks (SNNs), has recently gained immense popularity in machine learning community. It aims to offer reduced learning complexity, energy and latency through sparse event-driven computations, enabling real-time and sequential edge applications. However, due to their asynchronous spatio-temporal compute, SNNs require specialized sensing as well as algorithms and are not compatible with deployment on standard machine learning hardware such as GPUs. To that effect, there needs to be an end-to-end paradigm shift, from sensors to learning algorithms to the underlying hardware architectures. In this paper, we provide a perspective on the various efforts by the research community towards overcoming these challenges and realizing truly brain-inspired efficient machine intelligence.