The Machine Learning Hub Seminar Series presents:
Towards an AI Scientist – Foundational Machine Learning for Causality inspired from and applied to Living Systems
By Dr. Jesper Tegnér, professor in bioscience and a professor of computer science at KAUST; he also co-chairs the track on Bioinformatics and Machine Learning in KAUST’s new Bioengineering Program.
Wednesday, November 20, 2019
12:00 p.m. – 1:00 p.m.
Engineering Science Hall (building 9), hall 2
Abstract:
Nature generates data such as discrete objects, patterns, or as a temporal evolution of a particular process. Fundamentally, scientists search for an explanation; what are the causes, generative mechanisms? Historically, the existence of first principles (e.g., conservation, symmetry, action integrals) has made it possible to formulate explanatory, predictive, quantitative mathematical models in physics and to some extent in chemistry. Yet, in most areas of sciences, and in the life sciences in particular, we have data, often sparse, but no equations or first principles. Can we construct intelligent scientific machines that can generate a family of predictive quantitative causal models given a set of data?
In this talk, in the domain of biology and medicine, Prof. Tegnér will address challenges and opportunities in the light of this question by using work in network biology and medicine and deep analysis of cells—the building blocks of living systems. These examples set the stage for data-driven manifold learning targeting interpretable latent spaces. Secondly, explainable causal machine learning models beyond black-box solutions in part based on “classical mathematics.” Finally, he will present recent work in a discrete setting, on using algorithmic information theory, for the discovery of causality from observations in a rule-based context.
To read his bio and learn more about his work; check out his page here.
KAUST Machine Learning Hub