Quality of Machine Learning ModelsSpecial Guest!
The understanding of quality for machine learning models can differ significantly from traditional software engineering. For instance, rather than trying to eliminate all possible errors over time, we accept that models will still be wrong and are suspicious of those that claim to be 100% correct.
This session will discuss criteria and strategies to evaluate the quality of a machine learning model, focusing on its performance and fairness for the intended purpose.
Giovanni has been in IT for over 25 years, in roles ranging from consultant to software engineer, architect and now machine learning engineer. He holds a master's degree in electronic engineering and another in intelligent systems. He works mainly with Google Public Sector partners and customers to solve real-world problems in areas such as natural language processing, image processing, anomaly detection. He contributes back to the community of practitioners by presenting at workshops and authoring articles.