Search papers, labs, and topics across Lattice.
This work was supported by the Department of Computer Engineering, Faculty of Engineering, University of Peradeniya, Sri Lanka.All authors are with the Department of Computer Engineering, Faculty of Engineering, University of Peradeniya, Peradeniya 20400, Sri Lanka (e-mail: {e19129, e19275, e19309, e18379, e18147, roshanr, isurunawinne}@eng.pdn.ac.lk).Corresponding author: M.S. Peeris (e-mail: e19275@eng.pdn.ac.lk)
2
0
6
Achieve energy-efficient, accurate spiking neural network inference on the edge with a RISC-V SoC that consumes just 1.05 pJ per synaptic operation.
Diffusion models can generate synthetic cardiac MRIs that balance image quality, downstream task performance, and patient privacy better than flow-based alternatives, offering a promising route to data augmentation in medical imaging.
