Diffractive Optical Neural Network

Cross-source consensus on Diffractive Optical Neural Network from 1 sources and 5 claims.

1 sources · 5 claims

How it works

The system uses alternating learned phase modulation and free-space propagation operators. — Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification
Each diffractive layer applies a learned phase-only modulation profile over the spatial grid. — Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification
Local phase modulation becomes globally mixed after propagation because free-space propagation mixes spatial frequencies. — Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification
In this optical setting, depth increases the complexity of the realizable linear field transformation rather than composing nonlinear activations. — Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification
Three diffractive layers are justified because early layers provide the largest redistribution of digit-field energy while later layers refine detector separation. — Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification