Bio-plausible artificial intelligence
Priyadarshini Panda's research focuses on building efficient, robust, reliable machine intelligence grounded in bio-plausibility. 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 the "appropriateness" of intelligent systems, including 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 the Internet of Things and the necessity to embed intelligence in all technology around us, Panda's research aims to explore energy-accuracy-appropriateness tradeoff cohesively with algorithm hardware co-design to create truly functional intelligent systems. The Intelligent Computing Lab is 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.
Methods
Topics
Biography
Panda is Assistant Professor of Electrical and Computer Engineering at Yale. She received her BE and Master's degree from the Birla Institute of Technology and Science in 2013 and her PhD from Purdue University in 2019. During her PhD, she interned at Intel Labs, where she developed large-scale spiking neural network algorithms for benchmarking the Loihi chip.