A new artificial synapse, controlled entirely by light, enables in-sensor neuromorphic processing for more efficient and noise-resistant imaging systems.
Key Details
- 1Researchers engineered a synaptic device using a rare-earth-doped crystal with persistent optical afterglow.
- 2The synapse uses light for both input and state update, avoiding electrical signals and reducing energy demands.
- 3It mimics neural plasticity, showing both signal enhancement (UV facilitates) and suppression (near-infrared depresses).
- 4Integration with a silicon imaging sensor led to a neuromorphic camera prototype capable of in-sensor contrast enhancement and denoising.
- 5Neural networks using this optical synapse achieved nearly 96% accuracy in digit recognition, vs. 78% without the technique.
Why It Matters
By combining sensing, memory, and processing using optical signals, this approach points towards future imaging systems—potentially relevant to clinical imaging and radiology AI—that are faster, more power-efficient, and intrinsically robust to noise.
Source
EurekAlert
Related News
•EurekAlert
AI Unlocks Hidden Brain Lesions in Multiple Sclerosis via MRI
AI-enabled image processing reveals invisible cortical lesions in MRI scans of MS patients, advancing diagnosis and research.
•EurekAlert
AI-Driven Molecular Profiling Enhances Thrombosis Risk Prediction
Researchers create an AI model integrating genetic, clinical, and transcriptomic data to identify individuals at risk for thrombosis.
•EurekAlert
USC Receives $3M Gift for Alzheimer's Research Involving Imaging and AI
A $3 million donation to USC will accelerate Alzheimer's research, including imaging modality development and AI-based molecular analysis.