Scientific discovery is an interplay between observation and experimentation, and this talk looks at how machine learning can guide scientists towards better experiments. We discuss our experience in CSIRO, where we are researching, developing, and applying machine learning for scientific discovery.

In this seminar, we will look at the popular phrase "AI for Science" from multiple perspectives. We consider the goal of designing an experiment such that the measured output is maximised, and illustrate it with an example from genome biology. This workflow is an illustration of the general workflow of the scientific method, and we will use it to think about how machine learning augments each step. We will discuss adaptive experimental design, which uses data from previous experiments to train machine learning algorithms to recommend new experiments. We conclude by discussing opportunities and challenges in machine learning for scientific discovery.

Cheng Soon Ong is an Associate Science Director at Data61, CSIRO and a senior principal research scientist at the Statistical Machine Learning Group. He works on extending machine learning methods and enabling new approaches to scientific discovery, and has led the machine learning and artificial intelligence future science platform at CSIRO. He supervises and mentors many junior scientists, collaborates with scientists on problems in genomics and astronomy, advocates for open science, and is an adjunct Associate Professor at the Australian National University. He is co-author of the textbook Mathematics for Machine Learning, and his career has spanned multiple roles in Malaysia, Germany, Switzerland, and Australia.