In this talk I describe how a standard silicon transistor can be biased in an unconventional manner to produce neural and synaptic behavious, whcih are very useful to implement spiking neural networks for low-energy artificial intellicenge deployment on edge devices. More information in: S. Pazos et al. Nature 640, 69–76 (2025), https://doi.org/10.1038/s41586-025-08742-4
