Neuromorphic Computing for Future Breakthroughs in AI
Deep artificial neural networks have provided breakthroughs in AI in the form of near-human levels of data perception in many problem domains. Neuromorphic computing aims to take this a step further – chips directly inspired by the form and function of biological neural circuits so they can process new knowledge, adapt, behave, and learn in real time at extremely low power levels. After several decades of research at the intersection of neuroscience and silicon engineering, this technology is now reaching maturity. Progress in the field has advanced rapidly in recent years and, today, leading neuromorphic chips such as Intel’s Loihi research processor have a growing body of results showing quantitative gains compared to conventional architectures. The results point to compelling performance trends over a diverse range of problems as these systems are scaled up to millions of neurons, providing a roadmap for continued breakthroughs in AI.