InProgress Research Inc. Launches EDGE-AI,  its first investment in technology & product development. EDGE-AI will primarily focus on developing Machine Learning products and solutions geared for Critical Infrastructure applications. With the Critical Infrastructure focus, EDGE-AI will drive innovation in Machine Learning and Artificial Intelligence through introducing new ML methods, concepts and technologies best optimized for critical infrastructure environments, applications and limitations. We are very excited to be part of the Machine Learning transformation of Critical Infrastructure applications.  


While EDGE-AI will focus on developing ML technologies optimized for Critical Infrastructure applications. The integration of EDGE-AI machine learning products & solutions will be carried out through DESIAGO, IPR’s consulting & integration division. The ML solutions are intended to address existing domain challenges rule based programming can not currently tackle, and to complement our existing IIoT partners offerings.


EDGE-AI will work with IPR’s Industrial Internet of Things (IIoT) partners on integrating its new ML technologies into their products as well as supporting their ML product transformation through R&D collaboration. Our goal is to become the trusted go to partner, Critical Infrastructure vendors count on to assist with their ML transformation.


Why is Machine Learning for Critical Infrastructure different?

With the isolated nature of critical infrastructure networks, its very limited or no connectivity to the Internet, no Cloud access, no centralized global repository of data and not enough historical data to train ML models, comes the need to develop new unique Machine Learning approaches and techniques to better fit the environment and overcome its limitations. The use of current available ML technologies applicable for enterprise and commercial applications under the limitations described can yield ML models that fail to generalize properly with accuracy levels below what is acceptable. Due to the inherent issues caused by the isolated environment and limited availability of data, highly biased systems can develop with very low model generalization accuracy. The limitations can also make it not commercially feasible and/or be technically prohibitive to develop and train ML models.

EDGE-AI will focus on developing new non-orthodox approaches and techniques to address the limitations Machine Learning faces within Critical Infrastructure Applications, while benefiting from existing standard ML technologies. This will require changes in the principle approaches used to develop ML models, methods training, training duration as well as pushing some training and analytics to the edge. The Changes will call for next generation industrial grade edge processing hardware that we will coin as Edge Processing Unit (EPU) as well as Critical Infrastructure Machine Learning models that we will coin as Critical Infrastructure-ML (CI-ML) Models.


We look forward to being part of your Machine Learning transformation! 
InProgress Research Inc.
Toronto, Canada
Jun 24th, 2019