Hi all,I hope you've had a good start into 2019! This newsletter covers a ton of material: slides from the creator of BERT and on using transfer learning for dialogue; an MIT lecture on the Deep Learning state of the art as of 2019, Gaussian Processes, and VI from authorities in each area; NLP lesson curricula from CMU, Stanford, and Berkeley and new lessons from fast.ai to kick-start your learning in the new year; an overview of some of the cool things people have been doing with BERT; a discussion of DeepMind's AlphaStar; key takeaways on how to manage research teams; new resources containing the state of the art, lecture slides, and a guide on how to debug your neural network; a long list of tools and exciting new ML packages; loads of articles and blog posts; and exciting new research papers.A new section 🤓 This newsletter contains a new section, Meaningful Measures, inspired by FiveThirtyEight's Significant Digits. In this section, I'll list numbers related to ML and NLP that stuck out to me in the last month.Contributions 💪 If you have written or have come across something that would be relevant to the community, hit reply on the issue so that it can be shared more widely.I really appreciate your feedback, so let me know what you love ❤️ and hate 💔 about this edition. Simply hit reply on the issue.If you were referred by a friend, click here to subscribe. If you enjoyed this issue, give it a tweet 🐦.
Share this post
BERT, Transfer learning for dialogue, Deep…
Share this post
Hi all,I hope you've had a good start into 2019! This newsletter covers a ton of material: slides from the creator of BERT and on using transfer learning for dialogue; an MIT lecture on the Deep Learning state of the art as of 2019, Gaussian Processes, and VI from authorities in each area; NLP lesson curricula from CMU, Stanford, and Berkeley and new lessons from fast.ai to kick-start your learning in the new year; an overview of some of the cool things people have been doing with BERT; a discussion of DeepMind's AlphaStar; key takeaways on how to manage research teams; new resources containing the state of the art, lecture slides, and a guide on how to debug your neural network; a long list of tools and exciting new ML packages; loads of articles and blog posts; and exciting new research papers.A new section 🤓 This newsletter contains a new section, Meaningful Measures, inspired by FiveThirtyEight's Significant Digits. In this section, I'll list numbers related to ML and NLP that stuck out to me in the last month.Contributions 💪 If you have written or have come across something that would be relevant to the community, hit reply on the issue so that it can be shared more widely.I really appreciate your feedback, so let me know what you love ❤️ and hate 💔 about this edition. Simply hit reply on the issue.If you were referred by a friend, click here to subscribe. If you enjoyed this issue, give it a tweet 🐦.