As artificial intelligence (AI) transitions from cloud-centric operations to edge devices, the hardware that powers AI is undergoing significant change. While graphics processing units (GPUs) have long dominated both AI training and deployment, neural processing units (NPUs) are now emerging as a viable alternative, particularly for edge applications, according to Jeffrey Chen, vice president of product marketing at Kneron. Chen elaborated on these evolving trends at the recent Human-Machine Co-Creation New Era annual summit.