Bio-plausible artificial intelligence
Today, artificial intelligence is broadly pursued by Deep learning and Neuromorphic Computing researchers in the design space of energy-accuracy tradeoff with the motif of creating a machine exhibiting brain-like cognitive ability with brain-like efficiency. However, there are several questions regarding what I term as appropriateness of intelligent systems: robustness, explainability, security in adversarial scenarios, adaptivity or lifelong learning in a real-time complex environment and compatibility with hardware stack. With the advent of Internet of Things and the necessity to embed intelligence in all technology that surrounds us, the aim of my research is to explore energy-accuracy-appropriateness tradeoff cohesively with algorithm hardware co-design to create truly functional intelligent systems. We are also interested in exploring bio-plausible algorithms-and-hardware guided by natural intelligence (how the brain learns, the internal fabric of the brain etc.) to define the next generation of robust and efficient AI systems for beyond-vision static recognition tasks with the ability to perceive, reason, decide autonomously in real-time. In summary, my research focus is towards building efficient, robust and reliable machine intelligence grounded with bio-plausibility. This is aligned with the Center for Neurocomputation and Machine Intelligence that is aimed at identifying abstractions from neuroscience that can be integrated in machine intelligence to make it richer and more flexible in terms of cognitive ability.
Priya Panda is an assistant professor in the electrical engineering department at Yale University, USA. She received her B.E. and Master's degree from BITS, Pilani, India in 2013 and her PhD from Purdue University, USA in 2019. During her PhD, she interned in Intel Labs where she developed large scale spiking neural network algorithms for benchmarking the Loihi chip.