<p>➀ The current state-of-the-art machine learning applications use deep neural network models that have become so large and complex that they have exceeded the limits of traditional electronic computing hardware.</p><p>➁ Researchers at MIT and other institutions have developed a new type of photonic chip that can overcome these barriers.</p><p>➂ The optical device can complete the key calculations of machine learning classification tasks in less than half a nanosecond while achieving an accuracy rate of over 92%.</p>
Related Articles
- Radeon AI Pro R9700 Arrives With 32GB VRAM For Machine Learning And More3 months ago
 - ADI eases AI-at-the-edge for Cortex-M44 months ago
 - Internal cameras refine touch sense in artificial hand5 months ago
 - A Laser with 'Eyes' and a 'Brain': Machine Learning Simplifies Industrial Laser Processes5 months ago
 - Reducing Calculation Costs for Reliable AI Responses6 months ago
 - 2D 32-bit RISC-V processor7 months ago
 - Using R To Analyse An IoT Connected Health Monitoring System7 months ago
 - AI Vehicle Predictive Maintenance7 months ago
 - Retrieval Augmented Generation Makes Reading Thick Books Obsolete7 months ago
 - An Important Advance in Analog Verification7 months ago