Get started with Neutrino on CMC AI cluster- An AI-Driven Optimizer for Cloud and Edge

With the emergence of deep neural networks (DNNs) on embedded systems and edge devices, algorithm and hardware developers alike must consider the significant computational requirements of DNNs. Each input classification can require millions of expensive floating-point operations, billions of parameters and significant power requirements, often not practical for many devices. To make deep learning more accessible and affordable, Deeplite created Neutirno, an automated optimization software that makes DNNs faster, smaller and more energy-efficient from cloud to edge computing. AI engineers simply need to specify their trained model, dataset and target constraints like accuracy and model size. Using the Neutrino software, we will show how users can automate model optimization into a matter of hours or days with little to no manual effort. We will showcase the platform’s ease of use and compelling results on convolutional neural networks. This is a great chance to learn about DNN model optimization, see how Neutrino works first-hand and get early access to the community version available through CMC AI cluster!

The agenda includes two main sessions. First, Dr. Yassine Hariri of CMC will present the CMC AI cluster, an accessible and powerful computing platform for CMC members to experiment and train AI models. Second, Yasser Idris will present Deeplite Neutrino, an automated software platform that enables AI engineers and researchers to create highly compact deep learning models optimized for their resource constraints. The webinar will conclude with an open discussion at the end. All participants are invited to bring their questions and ideas!

Speakers

Yasser Idris is a Principal Software Engineer with more than 17 years of experience in Software development with expertise that spans a broad spectrum in the software world, both across research and industry, from big data analytics and databases to mobile and web development.
Before joining Deeplite, he led the engineering team of the Data Analytics group at Qatar Computing Research Institute(QCRI). Before that, he was in the industry with several start-ups in Canada and Egypt. Yasser is a graduate of the Computer Science department, Faculty of Engineering, Alexandria University. His personal field interests are algorithm optimizations and complexity theory.

Dr. Yassine Hariri is a senior platform design engineer at CMC Microsystems with over 15 years of experience in advanced computing systems from the cloud to the edge, with a focus on artificial intelligence, computer vision, video, image and sensor fusion workloads acceleration, FPGA based prototyping, software stack, and domain-specific hardware architectures. Currently leading projects related to the specification, development, implementation, deployment, and support of the next generation of advanced computing infrastructure mainly FPGAs, GPUs, and Custom Hardware for AI applications. Dr. Hariri earned his B.A.Sc. in Computer Engineering from Ecole Marocaine des Sciences de l’ingénieur, Casablanca, Morocco, in 1998, and the M.S. and Ph.D. degrees from Ecole de Technologie Supérieure (ETS), Montreal, QC, Canada, in 2002 and 2008, respectively, all in electrical engineering.

View on YouTube