Presented By O'Reilly and Cloudera
Make Data Work
Dec 4–5, 2017: Training
Dec 5–7, 2017: Tutorials & Conference

Using the Iot + deep learning to track half a million faces in real time

Siddha Ganju (Deep Vision)
2:35pm3:15pm Wednesday, December 6, 2017
IoT and intelligent real-time applications, Machine Learning
Location: Summit 2 Level: Intermediate

Who is this presentation for?

  • Data scientists, deep learning enthusiasts, mobile developers, software architects, and investors

Prerequisite knowledge

  • A basic understanding of deep learning

What you'll learn

  • Learn how to develop energy-efficient deep learning solutions at the intersection between machine learning and computer architecture and deploy deep learning at scale for devices that have low compute available


We’ve come a long way since the advent of the IoT to a network of almost 30 billion IoT devices that include sensors and cameras. The data they gather and transmit is becoming increasingly complex. Siddha Ganju explains how deep learning can revolutionize IoT applications to recognize half a million faces at international airports using existing airport cameras.

Many mobile applications rely on cloud processing. However, as the network of IoT devices grows and privacy issues become more important, it is generally better to perform heavy sensing tasks locally on a device. This removes the latency cost and large data transmission costs from high sensor sampling frequency. Siddha outlines a solution that uses selective sampling to combat high sensor sampling frequency by making the sensors and cameras intelligent with deep learning.

Photo of Siddha Ganju

Siddha Ganju

Deep Vision

Siddha Ganju is a data scientist at Deep Vision, where she works on building deep learning models and software for embedded devices. Siddha is interested in problems that connect natural languages and computer vision using deep learning. Her 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. She is a frequent speaker at conferences and advises the Data Lab at NASA. Siddha holds a master’s degree in computational data science from Carnegie Mellon University, where she worked on multimodal deep learning-based question answering. When she’s not working, you might catch her hiking.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)