Deep Learning on Mobile


Duration: 50 mins
Siddha Ganju
Self-driving Architect, NVIDIA

Over the last few years, convolutional neural networks (CNN) have risen in popularity, especially in the area of computer vision. Many mobile applications running on smartphones and wearable devices would potentially benefit from the new opportunities enabled by deep learning techniques. However, CNNs are by nature computationally and memory intensive, making them challenging to deploy on a mobile device. We explain how to practically bring the power of convolutional neural networks and deep learning to memory and power-constrained devices like smartphones. We’ll illustrate the value of these concepts with real-time demos as well as case studies from Google, Microsoft, Facebook and more. You will walk away with various strategies to circumvent obstacles and build mobile-friendly shallow CNN architectures that significantly reduce memory footprint.

You may also be interested in

25 mins
Dealing with Noobs: How to Work with Non-Technical People

The secret to being the hero of your story? Helping others be the hero of theirs. Take a business problem you...

50 mins
Application Security from the Inside Out

This talk tells the story of the implementation of an application security program in an agile, polyglot, cloud-first organisation. With fast-moving...

25 mins
Fostering Chaos Engineering Culture

In a digital world, users seek convenience when interacting with a business. Hence, it is imperative for businesses to make...

180 mins
Design Principles for the Effective Developer

How many design patterns and principles can you name as developer? Are they important? Should we not rather focus on...

50 mins
Leading & Guiding Development Teams

By definition, a tech leader is responsible for leading and guiding development teams. In this session we will take a...

25 mins
Sailing through Digital Transformation

The current health crisis is rapidly reshaping, for the better, what was already a key agenda for organizations in 2020...