Speaker Details

Christian D. Blakely

Head of Machine Learning and Artificial Intelligence @ PwC Switzerland

Christian started his career at NASA Goddard Space Flight Center in Washington DC as an atmospheric physicist. After completing a Ph.D. in Computational Science at University of Maryland, he had a 3 year long deep dive into big data and machine learning while doing a post-doctoral fellowship with the United States Department of Commerce. He moved to Switzerland to pursue a career in Europe, and now leads the machine learning and artificial intelligence efforts for PwC Switzerland, focusing on real-time machine learning technologies. He is also a part time classical concert pianist.

Real-Time Interpretable Machine Learning

We present a generalized machine learning framework for learning spatially and temporally in sequential data. While most machine learning techniques rely on dense connections of information (e.g. neural networks) that rely on derivatives, backpropagation, batch training, and regularization, rendering them incapable of learning in real-time, we show that machine learning can be done in real-time using sparse distributed representations (SDR) and bitwise operations. We also discuss the interpretability of the approach to yield more transparency in predictions. We conclude with some applications that are currently being used in various industries from anomaly detection, insider trading, and music.