Syntiant: Analog Deep Learning Chips
The chip they’ll be building is an inference accelerator designed to run deep-learning processes 50x more efficiently than traditional stored-program architectures, according to the company. The processor uses custom analog neural networks to optimize ...
The chip they’ll be building is an inference accelerator designed to run deep-learning processes 50x more efficiently than traditional stored-program architectures, according to the company. The processor uses custom analog neural networks to optimize ...
custom analog neural networks, traditional stored-program architectures, inference accelerator, deep-learning processes, chip, Company, Processor
