photoBig Data London: Data Gravity in the Clouds and at the Edge

Dave McCrory, VP of Engineering

photoDEEP LEARNING FOR MULTIMESSENGER ASTROPHYSICS:
REAL-TIME DISCOVERY AT SCALE

Joshua Bloom, Professor, UC Berkeley and VP of Data and Analytics

photoCTO Forum: RETHINK TECHNOLOGY “Practical Intelligent Systems”

Jeff Erhardt, VP of Intelligent Systems


photoMLconf: Counter Intuitive Machine Learning for Industrial IoT

Dr. June Andrews is a Principal Data Scientist at Wise.io, From GE Digital working on a machine learning and data science platform for the Industrial Internet of Things, which includes aviation, trains, and power plants. Previously, she worked at Pinterest spearheading the Data Trustworthiness and Signals Program to create a healthy data ecosystem for machine learning. She has also lead efforts at LinkedIn on growth, engagement, and social network analysis to increase economic opportunity for professionals. June holds degrees in applied mathematics, computer science, and electrical engineering from UC Berkeley and Cornell.

Abstract Summary:

Counter Intuitive Machine Learning for the Industrial Internet of Things:
The Industrial Internet of Things (IIoT) is the infrastructure and data flow built around the world’s most valuable things like airplane engines, medical scanners, nuclear power plants, and oil pipelines. These machines and systems require far greater uptime, security, governance, and regulation than the IoT landscape based around consumer activity. In the IIoT the cost of being wrong can be the catastrophic loss of life on a massive scale. Nevertheless, given the growing scale through the digitalization of industrial assets, there is clearly a growing role for machine learning to help augment and automate human decision making. It is against this backdrop that traditional machine learning techniques must be adapted and need based innovations created. We see industrial machine learning as distinct from consumer machine learning and in this talk we will cover the counterintuitive changes of featurization, metrics for model performance, and human-in-the-loop design changes for using machine learning in an industrial environment.