https://medium.com/cnn-digital/accelerating-ml-within-cnn-983f6b7bd2eb Accelerating ML within CNNKelly DavisMay 11 “Unfortunately, it was not designed for lightweight experimentation, and because of that, the research iteration process was frustratingly slow… we explored a number
What I Read: Do Wide and Deep Networks Learn the Same Things?
https://ai.googleblog.com/2021/05/do-wide-and-deep-networks-learn-same.html Do Wide and Deep Networks Learn the Same Things?Tuesday, May 4, 2021Posted by Thao Nguyen, AI Resident, Google Research
What I Read: Neural Nets Solve World’s Hardest Equations Faster
https://www.quantamagazine.org/new-neural-networks-solve-hardest-equations-faster-than-ever-20210419/ Latest Neural Nets Solve World’s Hardest Equations Faster Than Ever BeforeAnil AnanthaswamyContributing WriterApril 19, 2021 “Two new approaches allow deep neural networks to solve entire families of partial differential
What I Read: RL, Decentralized Multi-agent Navigation
https://ai.googleblog.com/2021/04/model-based-rl-for-decentralized-multi.html Model-Based RL for Decentralized Multi-agent NavigationWednesday, April 28, 2021Posted by Rose E. Wang, Student Researcher and Aleksandra Faust, Staff Research Scientist, Google Research “… in many real-world applications aligning
What I Read: Parallel Bayesian Optimization
https://medium.com/riskified-technology/from-sequential-to-parallel-a-story-about-parallel-bayesian-hyperparameter-optimization-f124ed29f556 From Sequential to Parallel, a story about Bayesian Hyperparameter OptimizationAndres AsaraviciusApr 26 “The goal of this process is to find the best set of parameters, and our goal was