2021 – Page 4 – Andrew Fairless, Ph.D.

What I Read: binary cross-entropy, log loss

By Andrew Fairless on October 25, 2021October 16, 2021

https://towardsdatascience.com/understanding-binary-cross-entropy-log-loss-a-visual-explanation-a3ac6025181a?gi=375ce73be21b Understanding binary cross-entropy / log loss: a visual explanationDaniel GodoyNov 21, 2018 “If you are training a binary classifier, chances are you are using binary cross-entropy / log lossContinue readingWhat I Read: binary cross-entropy, log loss

What I Read: Machine learning is not nonparametric statistics

By Andrew Fairless on October 20, 2021October 16, 2021

https://www.argmin.net/2021/10/13/prediction/ Machine learning is not nonparametric statistics.Ben RechtOct 13, 2021 “…I’ve been told by respected statisticians that machine learning is nothing more than nonparametric statistics. The longer I work inContinue readingWhat I Read: Machine learning is not nonparametric statistics

What I Read: How Animals Map 3D Spaces

By Andrew Fairless on October 19, 2021October 16, 2021

https://www.quantamagazine.org/how-animals-map-3d-spaces-surprises-brain-researchers-20211014/ How Animals Map 3D Spaces Surprises Brain ResearchersJordana CepelewiczOctober 14, 2021 When animals move through 3D spaces, the neat system of grid cell activity they use for navigating onContinue readingWhat I Read: How Animals Map 3D Spaces

What I Read: Wavelets Transform Data

By Andrew Fairless on October 18, 2021October 16, 2021

https://www.quantamagazine.org/how-wavelets-allow-researchers-to-transform-and-understand-data-20211013/ How Wavelets Allow Researchers to Transform, and Understand, DataAlexander HellemansContributing WriterOctober 13, 2021 “Built upon the ubiquitous Fourier transform, the mathematical tools known as wavelets allow unprecedented analysis andContinue readingWhat I Read: Wavelets Transform Data

What I Read: Mystery of Deep Learning

By Andrew Fairless on October 13, 2021October 12, 2021

https://www.quantamagazine.org/a-new-link-to-an-old-model-could-crack-the-mystery-of-deep-learning-20211011/ A New Link to an Old Model Could Crack the Mystery of Deep LearningTo help them explain the shocking success of deep neural networks, researchers are turning to olderContinue readingWhat I Read: Mystery of Deep Learning

What I Learn: Scaling TensorFlow

By Andrew Fairless on October 12, 2021September 24, 2021

https://arxiv.org/abs/2109.09541 Scaling TensorFlow to 300 million predictions per secondJan Hartman, Davorin Kopič “In this work, we describe the process of scaling machine learning models implemented in the TensorFlow machine learningContinue readingWhat I Learn: Scaling TensorFlow

What I Learn: Robots Must Be Ephemeralized

By Andrew Fairless on October 11, 2021September 24, 2021

https://blog.evjang.com/2021/09/ephemeralization.html Robots Must Be EphemeralizedEric JangMonday, September 20, 2021 “I now believe that offline evaluation technology is no longer optional if you are studying general-purpose robots… I outline why itContinue readingWhat I Learn: Robots Must Be Ephemeralized

What I Read: Bayesian Media Mix Modeling

By Andrew Fairless on October 7, 2021September 21, 2021

Bayesian Media Mix Modeling for Marketing OptimizationBenjamin Vincent2021-09-17 “Fortunately, with Bayesian modeling, we can do better than this! So-called Media Mix Modelling (MMM) can estimate how effective each advertising channelContinue readingWhat I Read: Bayesian Media Mix Modeling

What I Read: learning-to-rank

By Andrew Fairless on October 6, 2021September 21, 2021

https://www.amazon.science/blog/using-learning-to-rank-to-precisely-locate-where-to-deliver-packages Using learning-to-rank to precisely locate where to deliver packagesModels adapted from information retrieval deal well with noisy GPS input and can leverage map information.By George FormanSeptember 15, 2021 “ForContinue readingWhat I Read: learning-to-rank

What I Read: Permutation-Invariant Neural Networks for Reinforcement Learning

By Andrew Fairless on October 5, 2021September 21, 2021

https://arxiv.org/abs/2109.02869v1 The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement LearningYujin Tang, David Ha “…we build systems that feed each sensory input from the environment into distinct, butContinue readingWhat I Read: Permutation-Invariant Neural Networks for Reinforcement Learning

Year: 2021