Now published in Nature Photonics doi.org/10.1038/s41566… Congratulations to my colleagues Mandar Sohoni, Tianyu Wang , Peter McMahon , Martin Stein , Shi-Yuan Ma, Tatsuhiro Onodera and Maxwell Anderson

Our demonstration of a Multilayer spintronic neural networks with radiofrequency connections is out: nature.com/articles/s4156…

The energy efficiency of computing is ultimately limited by noise, with quantum noise as the fundamental floor. What happens if we operate an optical neural network with such low power that each neuron activation is caused by just a single photon? 1/5

*What more can neuromorphic computing learn from neuroscience?* We were asked to write an opinion piece for the journal Neuron and took the opportunity to propose some questions to the neuroscience community: arxiv.org/abs/2310.18335 1/4

Our opinion piece, "The hardware is the software", is now out in print: authors.elsevier.com/a/1iEjY3BtfH5N…

With AI advancing rapidly, there's been a push for more energy-efficient and faster alternatives to traditional digital silicon-based computers. *Analog physical neural networks* are promising candidates, but face challenges due to their intrinsically low precision. 1/