GRID.ai's Lead AI Educator Sebastian Raschka
How AI Happens
English - April 21, 2022 19:24 - 31 minutes - 25.7 MB - ★★★★★ - 10 ratingsTechnology Science Mathematics autonomous computer science computer vision big data training data artificial intelligence machine learning Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Joining us today on How AI Happens is Sebastian Raschka, Lead AI educator at GRID.ai and Assistant Professor of Statistics at the University of Wisconsin-Madison. Sebastian fills us in on the coursework he’s creating in his role at GRID.ai, and we find out what can be attributed to the crossover of machine learning in academia and the private sector. We speculate on the pros and cons of the commodification of deep learning models and which machine learning framework is better: PyTorch or TensorFlow.
Key Points From This Episode:
Sebastian Raschka’s journey from the computation of biology to AI and machine learning.The focus of his current role as Lead AI educator at GRID.ai.The ideal applications and outcomes of the coursework Sebastian is developing.The crossover of machine learning in academia and the private sector; the theory versus the application.Deep learning versus machine learning and what constitutes a deep learning problem.The importance of sufficient data for deep learning to be effective.The applications of the BERT text model.The pros and cons of developing more accessible models.Why Sebastian set out to write Machine Learning with PyTorch and Scikit-Learn.The structure of the book, including theory and application.Why Sebastian prefers PyTorch over TensorFlow.What he finds most exciting in the current deep learning space.The emerging opportunities to use deep learning!Tweetables:
“In academia, the focus is more on understanding how deep learning works… On the other hand, in the industry, there are [many] use cases of machine learning.” — @rasbt [0:10:10]
“Often it is hard to formulate answers as a human to complex questions.” — @rasbt [0:12:53]
“In my experience, deep learning can be very powerful but you need a lot of data to make it work well.” — @rasbt [0:14:06]
“In [Machine Learning with PyTorch and Scikit-Learn], I tried to provide a resource that is a hybrid between more theoretical books and more applied books.” — @rasbt [0:23:21]
“Why I like PyTorch is that it gives me the readability [and] flexibility to customize things.” — @rasbt [0:25:55]
Links Mentioned in Today’s Episode:
Machine Learning with PyTorch and Scikit-Learn