Probing optimisation in physics-informed neural networks
Nayara Fonseca, Veronica Guidetti, et al.
ICLR 2023
Deep learning has achieved outstanding success in several artificial intelligence (AI) tasks, resulting in human-like performance, albeit at a much higher power than the ~20 watts required by the human brain. We have developed an approach that incorporates biologically inspired neural dynamics into deep learning using a novel construct called spiking neural unit (SNU). Remarkably, these biological insights enabled SNU-based deep learning to even surpass the state-of-the-art performance while simultaneously enhancing the energy-efficiency of AI hardware implementations.
Nayara Fonseca, Veronica Guidetti, et al.
ICLR 2023
Craig Mahlasi, Sibusisiwe Makhanya, et al.
DS-I Africa Consortium Meeting 2023
Stanisław Woźniak, Hlynur Jónsson, et al.
Nature Communications
Leonard-Alexander Lieske, Aaron H. Oechsle, et al.
ACS Nano