2021 – Page 5 – Andrew Fairless, Ph.D.

What I Read: Deep One-class Classification

By Andrew Fairless on October 4, 2021September 21, 2021

https://arxiv.org/abs/2011.02578 Learning and Evaluating Representations for Deep One-class ClassificationKihyuk Sohn, Chun-Liang Li, Jinsung Yoon, Minho Jin, Tomas Pfister “We present a two-stage framework for deep one-class classification. We first learnContinue readingWhat I Read: Deep One-class Classification

What I Read: introduction to machine learning compilers and optimizers

By Andrew Fairless on September 30, 2021September 21, 2021

https://huyenchip.com//2021/09/07/a-friendly-introduction-to-machine-learning-compilers-and-optimizers.html A friendly introduction to machine learning compilers and optimizersChip HuyenSep 7, 2021 “…especially when running an ML model on the edge, the model’s success still depends on the hardwareContinue readingWhat I Read: introduction to machine learning compilers and optimizers

What I Read: Understanding Convolutions on Graphs

By Andrew Fairless on September 29, 2021September 21, 2021

https://distill.pub/2021/understanding-gnns/ Understanding Convolutions on GraphsUnderstanding the building blocks and design choices of graph neural networks.Ameya DaigavaneBalaraman RavindranGaurav AggarwalGoogle ResearchSept. 2, 202110.23915/distill.00032 “Graph neural networks (GNNs) are a family of neuralContinue readingWhat I Read: Understanding Convolutions on Graphs

What I Read: Introduction to Graph Neural Networks

By Andrew Fairless on September 28, 2021September 21, 2021

https://distill.pub/2021/gnn-intro/ A Gentle Introduction to Graph Neural NetworksBenjamin Sanchez-LengelingEmily ReifAdam PearceAlex WiltschkoGoogle ResearchSept. 2, 202110.23915/distill.00033 “Neural networks have been adapted to leverage the structure and properties of graphs. We exploreContinue readingWhat I Read: Introduction to Graph Neural Networks

What I Read: How Computationally Complex Is a Neuron?

By Andrew Fairless on September 27, 2021September 21, 2021

https://www.quantamagazine.org/how-computationally-complex-is-a-single-neuron-20210902/ How Computationally Complex Is a Single Neuron?by Allison Whitten “Computational neuroscientists taught an artificial neural network to imitate a biological neuron. The result offers a new way to thinkContinue readingWhat I Read: How Computationally Complex Is a Neuron?

What I Read: How Generally Capable Agents Trained

By Andrew Fairless on September 23, 2021September 4, 2021

https://www.lesswrong.com/posts/DreKBuMvK7fdESmSJ/how-deepmind-s-generally-capable-agents-were-trained How DeepMind’s Generally Capable Agents Were Trainedby 1a3orn20th Aug 2021 “One of DeepMind’s latest papers… explains how DeepMind produced agents that can successfully play games as complex as hide-and-seekContinue readingWhat I Read: How Generally Capable Agents Trained

What I Read: AI Story Generation

By Andrew Fairless on September 22, 2021September 4, 2021

https://thegradient.pub/an-introduction-to-ai-story-generation/ An Introduction to AI Story Generation21.Aug.2021Mark Riedl “To tell a story, an intelligent system has to have a lot of knowledge, both about how to tell a story andContinue readingWhat I Read: AI Story Generation

What I Read: Dissecting “Noise”

By Andrew Fairless on September 21, 2021September 4, 2021

https://www.lareviewofbooks.org/article/dissecting-noise/ Dissecting “Noise”By Vasant DharAUGUST 9, 2021 “WHAT IS NOISE? If two felons receive sentences of three years and seven years when they should both be sentenced to five, theContinue readingWhat I Read: Dissecting “Noise”

What I Read: Learning Neural Network Subspaces

By Andrew Fairless on September 20, 2021September 4, 2021

https://arxiv.org/abs/2102.10472 Learning Neural Network SubspacesMitchell Wortsman, Maxwell Horton, Carlos Guestrin, Ali Farhadi, Mohammad Rastegari “These neural network subspaces contain diverse solutions that can be ensembled, approaching the ensemble performance ofContinue readingWhat I Read: Learning Neural Network Subspaces

What I Read: To Learn, Brain Cells Break DNA

By Andrew Fairless on September 18, 2021September 4, 2021

https://www.quantamagazine.org/brain-cells-break-their-dna-to-learn-more-quickly-20210830/ To Learn More Quickly, Brain Cells Break Their DNAJordana CepelewiczStaff WriterAugust 30, 2021 “New work shows that neurons and other brain cells use DNA double-strand breaks, often associated withContinue readingWhat I Read: To Learn, Brain Cells Break DNA

Year: 2021