GTC Silicon Valley-2019 ID:S91020:Featured Talk: Accelerating AI
The current revolution in deep learning has been enabled by hardware, and progress is gated by increasing hardware performance. In the absence of Moore's Law and Dennard scaling, process technology contributes little to increased performance. To continue progress in deep learning, we rely instead on improvements in algorithms, architecture, and circuits. This talk will discuss current work on advancing hardware for deep learning.