Researchers at the University of Tehran's College of Engineering Develop a Method to Reduce AI Hardware Power Consumption by 80%
Researchers at the School of Electrical and Computer Engineering, College of Engineering, University of Tehran, have developed a novel method for performing numerical computations in artificial intelligence hardware. Their proposed approach reduces power consumption by up to 80.3%, processing time by up to 68.3%, and hardware area by up to 92.1%, while maintaining AI model accuracy at a level close to that achieved by exact computational architectures.
Read More