MCDS Seminar Series: A journey from classic machine learning and optimisation to deep learning (VIDEO RECORDING AVAILABLE)

Image for MCDS Seminar Series: A journey from classic machine learning and optimisation to deep learning (VIDEO RECORDING AVAILABLE)

More Information

mcds@unimelb.edu.au

Melbourne Centre for Data Science Seminar Series continues in 2021!

We were pleased to host Jeremy Howard - data scientist, researcher, developer, educator and entrepreneur. Jeremy is a founding researcher at fast.ai, a Distinguished Research Scientist at the University of San Francisco, the chair of WAMRI, and is Chief Scientist at platform.ai. For more on Jeremy's career, please visit https://www.fast.ai/about/

Seminar Title: A journey from classic machine learning and optimisation to deep learning

Abstract:
For 20 years I used a wide variety of machine learning and optimisation algorithms to tackle predictive modelling challenges in many fields. But today, I find that deep learning gives me the best results for most problems I tackle, including solving problems that previously were out of reach. Furthermore, I find that deep learning generally requires less manual tweaking, leading to fewer errors and quicker results. I'll discuss what I've learned on this journey, and describe why I believe nearly all data scientists should invest heavily in becoming effective deep learning practitioners.