no code implementations • 11 Dec 2023 • William A. Borders, Advait Madhavan, Matthew W. Daniels, Vasileia Georgiou, Martin Lueker-Boden, Tiffany S. Santos, Patrick M. Braganca, Mark D. Stiles, Jabez J. McClelland, Brian D. Hoskins
Methods such as hardware-aware training, where substrate non-idealities are incorporated during network training, are one way to recover performance at the cost of solution generality.