machine learning – Page 52 – Andrew Fairless, Ph.D.

What I Read: Nitpicking ML Technical Debt

By Andrew Fairless on January 2, 2021December 22, 2020

https://matthewmcateer.me/blog/machine-learning-technical-debt/ Nitpicking Machine Learning Technical DebtRevisiting a resurging NeurIPS 2015 paper (and 25 best practices more relevant than that for 2020)May 10, 2020 “Now the Tech Debt Paper is makingContinue readingWhat I Read: Nitpicking ML Technical Debt

What I Read: Differentiable Reasoning over Text

By Andrew Fairless on January 1, 2021December 22, 2020

https://blog.ml.cmu.edu/2020/05/15/differentiable-reasoning-over-text/ Differentiable Reasoning over TextAuthorsBhuwan DhingraPublishedMay 15, 2020 “Modern search engines not only retrieve a list of pages relevant to a query but often try to directly answer our questionsContinue readingWhat I Read: Differentiable Reasoning over Text

What I Read: Flows for simultaneous manifold learning and density estimation

By Andrew Fairless on December 31, 2020December 20, 2020

https://arxiv.org/abs/2003.13913 Flows for simultaneous manifold learning and density estimationJohann Brehmer, Kyle Cranmer “We introduce manifold-learning flows (M-flows), a new class of generative models that simultaneously learn the data manifold asContinue readingWhat I Read: Flows for simultaneous manifold learning and density estimation

What I Read: Learning Neural Causal Models

By Andrew Fairless on December 30, 2020December 20, 2020

https://arxiv.org/abs/1910.01075Learning Neural Causal Models from Unknown InterventionsNan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Chris Pal, Yoshua Bengio “We present a new framework for meta-learning causal modelsContinue readingWhat I Read: Learning Neural Causal Models

What I Read: GPT-3, The New Mighty Language Model

By Andrew Fairless on December 28, 2020December 20, 2020

https://towardsdatascience.com/gpt-3-the-new-mighty-language-model-from-openai-a74ff35346fc?gi=a6255cca8370 GPT-3: The New Mighty Language Model from OpenAIPushing Deep Learning to the Limit with 175B ParametersMoiz SaifeeMay 31 “While this type of transfer learning obviates the need to useContinue readingWhat I Read: GPT-3, The New Mighty Language Model

What I Read: Self Supervised Representation Learning in NLP

By Andrew Fairless on December 28, 2020December 20, 2020

https://amitness.com/2020/05/self-supervised-learning-nlp/ Self Supervised Representation Learning in NLPPublished May 23, 2020 in nlp “While Computer Vision is making amazing progress on self-supervised learning only in the last few years, self-supervised learningContinue readingWhat I Read: Self Supervised Representation Learning in NLP

What I Read: ML models in production

By Andrew Fairless on December 27, 2020December 20, 2020

https://medium.com/analytics-and-data/overview-of-the-different-approaches-to-putting-machinelearning-ml-models-in-production-c699b34abf86 Overview of the different approaches to putting Machine Learning (ML) models in productionJulien KervizicApr 29, 2019 “There are different approaches to putting models into productions, with benefits that canContinue readingWhat I Read: ML models in production

What I Read: Symbolic Mathematics, Neural Networks

By Andrew Fairless on December 27, 2020December 20, 2020

https://www.quantamagazine.org/symbolic-mathematics-finally-yields-to-neural-networks-20200520/ artificial intelligenceSymbolic Mathematics Finally Yields to Neural NetworksAfter translating some of math’s complicated equations, researchers have created an AI system that they hope will answer even bigger questions.by StephenContinue readingWhat I Read: Symbolic Mathematics, Neural Networks

What I Read: Feature Management

By Andrew Fairless on December 25, 2020December 13, 2020

https://medium.com/@jrodthoughts/the-architecture-used-at-linkedin-to-improve-feature-management-in-machine-learning-models-c7bd6ae54db The Architecture Used at LinkedIn to Improve Feature Management in Machine Learning ModelsThe new typed feature schema streamlined the reusability of features across thousands of machine learning models.Jesus RodriguezAprContinue readingWhat I Read: Feature Management

What I Read: Deep Generative Models

By Andrew Fairless on December 25, 2020December 13, 2020

https://medium.com/@jrodthoughts/microsoft-research-unveils-three-efforts-to-advance-deep-generative-models-b1d2fe3395e8 Microsoft Research Unveils Three Efforts to Advance Deep Generative ModelsOptimus, FQ-GAN and Prevalent bring new ideas to apply generative models at large scale.Jesus RodriguezApr 27 “With the emergence ofContinue readingWhat I Read: Deep Generative Models

Tag: machine learning