Presented By O'Reilly and Cloudera
Make Data Work
March 13–14, 2017: Training
March 14–16, 2017: Tutorials & Conference
San Jose, CA

Squeezing deep learning onto mobile phones

Anirudh Koul (Microsoft)
11:50am12:30pm Wednesday, March 15, 2017
Data science & advanced analytics
Location: 210 C/G Level: Intermediate
Secondary topics:  Deep learning, Hardcore Data Science, Mobile
Average rating: ****.
(4.20, 5 ratings)

Who is this presentation for?

  • Data scientists, mobile developers, and software architects

Prerequisite knowledge

  • A high-level understanding of deep learning

What you'll learn

  • Learn how to deploy deep learning architectures on mobile devices
  • Gain practical tips on developing apps for real-world scenarios
  • Become familiar with the ecosystem and platforms available for AI on smartphones


Over the last few years, convolutional neural networks (CNN) have risen in popularity, especially in computer vision. Anirudh Koul explains how to bring the power of deep learning to memory- and power-constrained devices like smartphones and drones.

Many mobile applications running on smartphones and wearable devices would potentially benefit from the accuracy of deep learning techniques. Also, local execution allows data to stay on the mobile device, hence avoiding latency issues of data transmission to the cloud and also alleviating privacy concerns. However, CNNs, by nature, are computationally expensive and memory intensive, making them challenging to deploy on a mobile device. Anirudh explores various strategies to circumvent these obstacles and build mobile-friendly shallow CNN architectures to significantly reduce the memory footprint, making CNNs easier to store on a smartphone. By comparing a family of model compression techniques to prune the network size for live image processing, you can build a CNN version optimized for inference on mobile devices. Anirudh also covers practical strategies to preprocess your data in a manner that makes the models more efficient in the real world.

Anirudh showcases these techniques using a real-world project, as well as tips and tricks, to demonstrate how to get started developing your own deep learning application suitable for deployment on storage- and power-constrained mobile devices. Similar techniques can also be applied to make deep neural nets more efficient when deploying in a regular cloud-based production environment, reducing the number of GPUs required and optimizing on cost.

Photo of Anirudh Koul

Anirudh Koul


Anirudh Koul is a senior data scientist at Microsoft Research and the founder of Seeing AI, a talking camera app for the blind community. Anirudh brings over a decade of production-oriented applied research experience on petabyte-scale datasets, with features shipped to about a billion people. An entrepreneur at heart, he has run ministartup teams within Microsoft, prototyping ideas using computer vision and deep learning techniques for augmented reality, productivity, and accessibility and building tools for communities with visual, hearing, and mobility impairments. A regular at hackathons, Anirudh has won close to three dozen awards, including top-three finishes for four years consecutively in the world’s largest private hackathon, with 18,000 participants. Some of his recent work, which IEEE has called “life changing,” has been showcased at a White House event, on Netflix, and in National Geographic and received awards from the American Foundation for the Blind and Mobile World Congress.