Accelerating machine learning deployment in low-power embedded systems

07 October 2015 CEVA has introduced a real-time neural network software framework, the CEVA Deep Neural Network (CDNN), to streamline machine learning deployment in low-power embedded systems. Exploiting the processing power of the CEVA-XM4 imaging & vision DSP, the CDNN is claimed to enable embedded systems to perform deep learning tasks 3x faster than the leading GPU-based systems while consuming 30x less power and requiring 15x less memory bandwidth. For example, running a Deep Neural Network based pedestrian detection algorithm at 28nm requires less than 30mW for a 1080p 30fps video stream. Key to the performance, low power and low memory bandwidth capabilities of CDNN is the CEVA Network Generator, a proprietary automated technology that converts a customer’s network structure and weights to a slim, customised network model used in…


Link to Full Article: Accelerating machine learning deployment in low-power embedded systems