reinforcement learning – Page 5 – Andrew Fairless, Ph.D.

What I Read: Interpretability in Machine Learning

By Andrew Fairless on February 20, 2021January 21, 2021

https://thegradient.pub/interpretability-in-ml-a-broad-overview/ Interpretability in Machine Learning: An Overview21.Nov.2020Owen Shen “Broadly, interpretability focuses on the how. It’s focused on getting some notion of an explanation for the decisions made by our models….Continue readingWhat I Read: Interpretability in Machine Learning

What I Read: Revisiting Sutton’s Bitter Lesson for AI

By Andrew Fairless on February 15, 2021January 18, 2021

https://blog.exxactcorp.com/compute-goes-brrr-revisiting-suttons-bitter-lesson-artificial-intelligence/ Deep LearningCompute Goes Brrr: Revisiting Sutton’s Bitter Lesson for Artificial IntelligenceMarketing, October 27, 2020 “The main driver of AI progress, according to Sutton, is the increasing availability of computeContinue readingWhat I Read: Revisiting Sutton’s Bitter Lesson for AI

What I Read: Reinforcement learning is supervised learning

By Andrew Fairless on February 2, 2021January 8, 2021

https://bair.berkeley.edu/blog/2020/10/13/supervised-rl/ Reinforcement learning is supervised learning on optimized dataBen Eysenbach and Aviral Kumar and Abhishek Gupta Oct 13, 2020 “This suggests that we can simply use inverse RL to relabelContinue readingWhat I Read: Reinforcement learning is supervised learning

What I Read: Neural Architecture Search

By Andrew Fairless on January 26, 2021December 31, 2020

https://lilianweng.github.io/lil-log/2020/08/06/neural-architecture-search.html Neural Architecture SearchAug 6, 2020 by Lilian Weng “Automatically learning and evolving network topologies is not a new idea (Stanley & Miikkulainen, 2002). In recent years, the pioneering workContinue readingWhat I Read: Neural Architecture Search

What I Read: Multi-Armed Bandits and Experimentation

By Andrew Fairless on January 23, 2021December 30, 2020

https://multithreaded.stitchfix.com/blog/2020/08/05/bandits/ Multi-Armed Bandits and the Stitch Fix Experimentation PlatformBlog post by Brian AmadioBrian AmadioAugust 05, 2020 “Multi-armed bandits have become a popular alternative to traditional A/B testing for online experimentationContinue readingWhat I Read: Multi-Armed Bandits and Experimentation

What I Read: Traffic prediction with Graph Neural Networks

By Andrew Fairless on January 23, 2021December 30, 2020

https://deepmind.com/blog/article/traffic-prediction-with-advanced-graph-neural-networks Traffic prediction with advanced Graph Neural Networks “We discovered that Graph Neural Networks are particularly sensitive to changes in the training curriculum… the most successful approach to this problemContinue readingWhat I Read: Traffic prediction with Graph Neural Networks

What I Read: Artificial Intelligence Will Do What We Ask

By Andrew Fairless on December 9, 2020November 29, 2020

https://www.quantamagazine.org/artificial-intelligence-will-do-what-we-ask-thats-a-problem-20200130/ artificial intelligenceArtificial Intelligence Will Do What We Ask. That’s a Problem.Natalie WolchoverSenior Writer/EditorJanuary 30, 2020By teaching machines to understand our true desires, one scientist hopes to avoid the potentiallyContinue readingWhat I Read: Artificial Intelligence Will Do What We Ask

Tag: reinforcement learning