Artificial Intelligence #30

Hey! In this issue: learning to transform video into a cartoon, a game for learning reinforcement learning, understanding the effectiveness of ensembles of deep models, a tutorial on deep generative models, a paper explained, and more.

This week's issue is sponsored by the DATAcated Academy.

• Learning to transform video into a cartoon using white-box cartoon representations (video, code, paper)
• Open reinforcement learning benchmark that includes 34+ games and provides an unprecedented level of transparency, openness, and reproducibility (video, website, code)
• A game for learning the reinforcement learning (available on Steam)
• PyTorch v1.6 released
• [Sponsored] The visual best practices course from the DATAcated Academy

The Visual Best Practices Course from the DATAcated Academy trains data analysts to design effective and beautiful data visualizations. The content is product-agnostic; you'll learn best practices that you can apply to your data visualizations today!

• Big Bird: Transformers for longer sequences (paper, video explanation)
• Understanding the effectiveness of ensembles in deep learning
• Writing better code with PyTorch and einops
• Mathematics for machine learning - multivariate calculus (video)
• Tutorial on deep generative models (video, slides)
• [Paper Explained] Hopfield Networks is All You Need (video, paper, code)

If you build an AI or data product or service, you are invited to sponsor one of the next issues. Feel free to contact True Positive Inc. for more details on sponsorships.

Enjoy the newsletter? Help us make it bigger and better by sharing with your colleagues and friends.

Have a nice weekend! See you next week. — Andriy