Abstract: 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.
This workshop explains how to practically bring the power of convolutional neural networks and deep learning to memory and power-constrained devices like smartphones. You will learn various strategies to circumvent obstacles and build mobile-friendly shallow CNN architectures that significantly reduce the memory footprint and therefore make them easier to store on a smartphone; The workshop also dives into how to use a family of model compression techniques to prune the network size for live image processing, enabling you to build a CNN version optimized for inference on mobile devices. Along the way, you will learn practical strategies to preprocess your data in a manner that makes the models more efficient in the real world.
Following a step by step example of building an iOS deep learning app, we will discuss tips and tricks, speed and accuracy trade-offs, and benchmarks on different hardware to demonstrate how to get started developing your own deep learning application suitable for deployment on storage- and power-constrained mobile devices. You can also apply similar techniques to make deep neural nets more efficient when deploying in a regular cloud-based production environment, thus reducing the number of GPUs required and optimizing on cost.
Bio: Siddha Ganju is an Architect at Nvidia where she is working on the Self-Driving initiative and co-author of the upcoming book, ‘Practical Deep Learning for Cloud and Mobile’. She was previously at Deep Vision where she worked on developing and deploying deep learning models on resource constraint edge devices. She graduated from Carnegie Mellon University with a Master's in Computational Data Science. Her prior work ranges from Visual Question Answering to Generative Adversarial Networks to gathering insights from CERN's petabyte scale data and has been published at top tier conferences like CVPR and NIPS. She is a frequent speaker at AI conferences and is a NASA AI Advisor.