Optoelectronic Intelligence
arXiv:2010.08690 · doi:10.1063/5.0040567
Abstract
To design and construct hardware for general intelligence, we must consider principles of both neuroscience and very-large-scale integration. For large neural systems capable of general intelligence, the attributes of photonics for communication and electronics for computation are complementary and interdependent. Using light for communication enables high fan-out as well as low-latency signaling across large systems with no traffic-dependent bottlenecks. For computation, the inherent nonlinearities, high speed, and low power consumption of Josephson circuits are conducive to complex neural functions. Operation at 4\,K enables the use of single-photon detectors and silicon light sources, two features that lead to efficiency and economical scalability. Here I sketch a concept for optoelectronic hardware, beginning with synaptic circuits, continuing through wafer-scale integration, and extending to systems interconnected with fiber-optic white matter, potentially at the scale of the human brain and beyond.
10 pages, five figures, perspective article
References in corpus (8)
- Photonics for artificial intelligence and neuromorphic computing
- Attojoule Optoelectronics for Low-Energy Information Processing and Communications: a Tutorial Review
- A Survey of Neuromorphic Computing and Neural Networks in Hardware
- Six networks on a universal neuromorphic computing substrate
- Tutorial: Photonic Neural Networks in Delay Systems
- All-silicon light-emitting diodes waveguide-integrated with superconducting single-photon detectors
- Synchronization dynamics on the picosecond timescale in coupled Josephson junction neurons
- Fan-out and Fan-in properties of superconducting neuromorphic circuits