Machine learning is changing scientific research in many fields, but many scientists still doubt using methods that focus on prediction more than causal understanding.
That’s why we are excited to have Christoph Molnar return to the podcast with Timo Freiesleben. They are co-authors of "Supervised Machine Learning for Science: How to Stop Worrying and Love your Black Box." We will talk about the perceived problems with automation in certain sciences and find out how scientists can use machine learning without losing scientific accuracy.
Show notes
Introduction to machine learning for science (0:00)
Specific requirements for scientific modelers (1:47)
- Different scientific disciplines have varying goals beyond prediction, including control, explanation, and reasoning about phenomena
Benefits and limitations of ML in science (4:45)
- Traditional scientific approaches build models from simple to complex, while machine learning often starts with complex models
Scientists' concerns about machine learning (8:54)
- Scientists worry about using ML due to lack of interpretability and causal understanding
Embedding domain knowledge in ML models (12:40)
- ML can both integrate domain knowledge and test existing scientific hypotheses
Testing hypotheses: Medical device example (14:50)
- "Shortcut learning" occurs when models find predictive patterns that aren't meaningful
Current state and future of ML in science (19:00)
- Machine learning adoption varies widely across scientific fields
- Ecology and medical imaging have embraced ML, while other fields remain careful
- Future directions include ML potentially discovering scientific laws humans can understand
Closing and preview of part 2 (26:26)
- Researchers should view machine learning as another tool in their scientific toolkit
- In part 2, we'll shift the discussion with Christoph and Timo to talk about putting these concepts into practice.
Do you have questions about machine learning in the sciences?
Connect with us to comment on your favorite topics:
- LinkedIn - Episode summaries, shares of cited articles, and more.
- YouTube - Was it something that we said? Good. Share your favorite quotes.
- Visit our page - see past episodes and submit your feedback! It continues to inspire future episodes.
