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

Danielle Dean
Technical Director, Machine Learning, iRobot

Website | @danielleodean

Danielle Dean is the technical director of machine learning at iRobot. Previously, she was a principal data science lead at Microsoft. She holds a PhD in quantitative psychology from the University of North Carolina at Chapel Hill.

Sessions

12:05pm12:45pm Wednesday, December 6, 2017
Danielle Dean (iRobot), Wee Hyong Tok (Microsoft)
Average rating: ***..
(3.25, 4 ratings)
Transfer learning enables you to use pretrained deep neural networks (e.g., AlexNet, ResNet, and Inception V3) and adapt them for custom image classification tasks. Danielle Dean and Wee Hyong Tok walk you through the basics of transfer learning and demonstrate how you can use the technique to bootstrap the building of custom image classifiers. Read more.
11:15am11:55am Thursday, December 7, 2017
Wee Hyong Tok (Microsoft), Danielle Dean (iRobot)
Deep neural networks are responsible for many advances in natural language processing, computer vision, speech recognition, and forecasting. Danielle Dean and Wee Hyong Tok illustrate how cloud computing has been leveraged for exploration, programmatic training, real-time scoring, and batch scoring of deep learning models for projects in healthcare, manufacturing, and utilities. Read more.