17th INTERNATIONAL FORUM ON MPSoC
for software-defined hardware
For further information, please send email to Frédéric Pétrot
N2D2 : an open-source deep neural network design environmentDownload Slides
Artificial Neural networks are based on algorithms mimicking the way a biological brain behaves. Neural networks are playing an increasing role in giving objects and systems recognition capabilities by interpreting images, sounds, and other information generated by one or more sensors.
This year CEA LIST announces the availability of its neural network design environment named N2D2 in open-source!
N2D2 provides an end-to-end solution to DNN developers, covering every stage in the neural-network design and deployment process, whatever is the hardware solution targeted (CPU, GPU, FPGA...). N2D2 integrates the whole data-processing chain from data collection and conditioning to training, simulation, processing and performance benchmarking. N2D2 is already bringing solutions that meet CEA LIST partners’ needs such as Atos, ArcelorMittal, and Global Sensing Technologies.
Nicolas Ventroux is the head of the Computing and Design Environment Laboratory at CEA LIST. He received a M.Sc and a M.Eng. in Computer Sciences from INSA, Rennes in 2003, and the PhD degree in Electronics from the University of Rennes in 2006. He is a CEA Senior Expert in multiprocessor modeling and design, and was a project manager of many national and European projects. He was a scholar visitor at Carnegie Mellon University (CMU) in the CALCM laboratory in 2012. He wrote, as author and co-author, ten patents and several papers in conferences and journals in the multi and many-core domains. He is also a reviewer for several international conferences and journals since 2006.