<ul><li>WISE is a novel computing architecture for wireless edge networks designed to overcome energy constraints in deep learning inference.</li><li>It achieves this through two key innovations: disaggregated model access via wireless broadcasting and in-physics computation of complex-valued matrix-vector multiplications directly at radio frequency.</li><li>WISE achieves 95.7% image classification accuracy with ultra-low operation power of 6.0 fJ/MAC per client, resulting in a computation efficiency of 165.8 TOPS/W.</li><li>This approach enables energy-efficient deep learning inference on wirelessly connected edge devices, achieving over two orders of magnitude improvement compared to traditional digital computing.</li></ul>

Disaggregated Deep Learning via In-Physics Computing at Radio Frequency

Discover more