AI Is Giving Optical Computing Another Shot
Electrical EngineeringPhysics
THE AI ANGLE
Driving power demand through inference workloadsSurging energy demands from AI inference have led to rapid investment in optical computing startups. Researchers and engineers are building systems that run vector-matrix multiplication using free-space light, metamaterials, and integrated photonics. This effort forces hardware designers to balance optical scaling advantages against the electronic energy costs of data encoding.
THE TEACHING ANGLE
Consider whether the electrical energy required to encode data into light eliminates the efficiency gains of optical computing for smaller matrix sizes.Read the original at spectrum.ieee.org Generate teaching or study materials
More in Electrical Engineering
- Transformer shortages loom for strained US power gridPhys.org — Technology · November 18, 2026
- How brine processing could offset sulfur hexafluoride treatment costsPhys.org — Technology · November 18, 2026
- Electron fingerprints help AI predict complex alloy properties with little training dataPhys.org — Technology · November 18, 2026