On the right tracks with CD4ML

Asset management can be a tremendous task, whether its about roads, ports, utilities, or railroads. The configuration and condition of assets are mostly inspected and administered manually, multiple times a year. A labour-intensive job that is error prone and reactive to changes. Failing assets come as a surprise and wrong parts are ordered. Maarten helped to build a platform to automate asset management with machine learning. This platform ingests image and video data, along with meta data, of every inch of assets from multiple angles. These images, ranging in dozens of terabytes of data per campaign, are automatically processed in the data platform and prepared for analysis. Maarten's team developed several AI components and Machine Learning models to solve various problems, like asset recognition, segmentation, condition classification, and configuration correction. This way, inspection and configuration is checked automatically and a proactive approach is enabled. In this talk, Maarten (Data & AI Architect) will tell more about this use case. He will also dive into CD4ML (Continuous Delivery for Machine Learning), a technique that allows the platform to quickly expand with new AI components and Machine Learning models, from development into production in no-time. That was especially valuable since he had to deal with dozens of models.
Who is this presentation for?
Anyone working with data science / AI / ML in a project. From the ML engineer to the data scientist to the product owner and the manager.
Prerequisite knowledge:
Some general understanding of machine learning helps.
What you'll learn?
What CD4ML is and how it can benefit your team / project / company.

Maarten started programming at the age of 10, building web sites and desktop applications. Throughout secondary school, he worked at a software company, building SQL databases, reports, back-end applications and front end applications. After secondary school, Maarten obtained a Master of Science degree in Computer Science, specializing in Algorithmic Data Analysis. During his studies, he also worked at a start-up, building native mobile apps, mainly for marketing campaigns. After graduation, he became a Data Scientist. He worked for dozens of clients, in all sorts of sectors. For example, he helped save lives at a health insurance company, improved passenger flows through a large hub airport, help energy providers to boost the energy transition, generate more return, mitigate risk in financial investments, and so on. In recent years, Maarten worked more and more in the cloud and focusing on the architecture side of things. Maarten holds several Microsoft Certifications, including: Azure Solution Architect Expert, Azure AI Engineer, Azure Data Scientist, and Microsoft Certified Trainer.