Arm TechCon 2017 Schedule

View, browse and sort the list of sessions by Pass Type, Track, Day/Time, or by Speaker. Sessions are subject to change. Seating is on a first-come, first-served basis. Please arrive early to ensure you get a seat.

Build your conference agenda today! By signing up for the Scheduler, you can add sessions to your "Favorites" and develop your own personalized schedule. This personalized schedule will be synced with the official Arm TechCon Event App.

AI Beyond Cats & Cars

Pass Type: All-Access Pass - Get your pass now!
Track: Computer Vision, Machine Learning & Graphics
Format: 50-Minute Technical Session
Audience Level: Introductory
Recording: TBD

By now we very well know how to design and train a neural network to recognize cats, dogs and cars. But what about real projects — agriculture, construction, medical, retail? This how-to talk will provide an overview of what it takes to design, train, and fine-tune a real-life DNN-based embedded vision solution. Presentation will explore algorithmic, data set, training, and optimization decisions that take you from proofs-of-concepts to solid, reliable, and highly optimized systems. This material is based on our own successes, failures, and other lessons we learnt while implementing embedded vision solutions over the past few years

Takeaway

What it takes to succeed in a real-life development of a DNN-based embedded vision product? Learn how to plan and design for deep learning, how to select and cascade algorithms, where to get the training data and how much is enough, and how to optimize and troubleshoot your product.

Intended Audience

Engineering managers, product managers, architects, software and hardware engineers working on embedded vision systems