Subscribe Contact Us

Introducing

CEVA Deep
Neural Network

Accelerating Machine Learning
Deployment in Low-Power
Embedded Systems

The CEVA Deep Neural Network (CDNN) is a real-time, neural network software framework that streamlines machine learning deployment in low-power embedded systems.
Harnessing the processing power of the CEVA-XM4 imaging & vision DSP, the CDNN enables 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.
CDNN significantly simplifies the implementation of deep learning in embedded systems by:

Automatically converting offline pre-trained machine learning networks to real-time, embedded-ready networks

Enabling real-time high quality object recognition and vision analytics

Delivering the flexibility to support various neural network structures, including any number and type of layers

In the News

Embedded
Day 2 at the Embedded Vision Summit 2016 03 May 2016
EDN Europe
DESIGN WIN; DSP IP FROM CEVA IN V2X VEHICLE-TO-EVERYTHING CHIPSET 28 April 2016
SemiWiki
Self-contained low power Wi-Fi IP for IoT apps 13 April 2016
Need additional information? Click here to contact us