2021 – Page 8 – Andrew Fairless, Ph.D.

What I Read: Geometric, Deep Learning

By Andrew Fairless on August 16, 2021July 22, 2021

https://towardsdatascience.com/geometric-foundations-of-deep-learning-94cdd45b451d?gi=d7fa7307aa63 Geometric foundations of Deep LearningGeometric Deep Learning is an attempt for geometric unification of a broad class of ML problems from the perspectives of symmetry and invariance. These principlesContinue readingWhat I Read: Geometric, Deep Learning

What I Read: Training AI, Analogies

By Andrew Fairless on August 13, 2021July 22, 2021

https://www.quantamagazine.org/melanie-mitchell-trains-ai-to-think-with-analogies-20210714/ The Computer Scientist Training AI to Think With AnalogiesMelanie Mitchell has worked on digital minds for decades. She says they’ll never truly be like ours until they can makeContinue readingWhat I Read: Training AI, Analogies

What I Read: Building Data Platform

By Andrew Fairless on August 12, 2021July 22, 2021

https://www.montecarlodata.com/the-quick-and-dirty-guide-to-building-your-data-platform/ Updated July 9, 2021The Quick and Dirty Guide to Building Your Data PlatformBarr Moses, Lior Gavish“For most organizations, building a data platform is no longer a nice-to-have but aContinue readingWhat I Read: Building Data Platform

What I Read: Identifying Document Types

By Andrew Fairless on August 11, 2021July 22, 2021

https://tech.scribd.com/blog/2021/identifying-document-types.html Identifying Document Types at ScribdJonathan RamkissoonJuly 12, 2021 “User-uploaded documents have been a core component of Scribd’s business from the very beginning, understanding what is actually in the documentContinue readingWhat I Read: Identifying Document Types

What I Read: Data Science Peer Review

By Andrew Fairless on August 10, 2021July 22, 2021

https://towardsdatascience.com/postmortem-a-year-of-data-science-peer-review-in-startups-7e9cc2862ed9 Postmortem: A Year of Data Science Peer Review in StartupsShay PalachyJul 7 “About a year ago I suggested two peer review processes for data science projects… I have hadContinue readingWhat I Read: Data Science Peer Review

What I Read: Prompting, Language Models, NLP

By Andrew Fairless on August 9, 2021July 22, 2021

https://thegradient.pub/prompting/ Prompting: Better Ways of Using Language Models for NLP Tasks03.Jul.2021Tianyu Gao “The giant model size of GPT-3 is an important factor for its success, while the concept of promptsContinue readingWhat I Read: Prompting, Language Models, NLP

What I Read: Abstraction, Data Science

By Andrew Fairless on August 6, 2021July 22, 2021

https://www.linkedin.com/pulse/abstraction-data-science-great-combination-venkat-raman Abstraction and Data Science – Not a great combinationPublished on July 8, 2021Venkat RamanCo-Founder at Aryma Labs “Firstly, in normal programming, if you do abstraction, you just abstract awayContinue readingWhat I Read: Abstraction, Data Science

What I Read: Understanding Levenshtein Distance

By Andrew Fairless on August 5, 2021July 12, 2021

https://medium.com/@ethannam/understanding-the-levenshtein-distance-equation-for-beginners-c4285a5604f0 Understanding the Levenshtein Distance Equation for BeginnersEthan NamFeb 26, 2019 “The Levenshtein distance is a number that tells you how different two strings are. The higher the number, theContinue readingWhat I Read: Understanding Levenshtein Distance

What I Read: Neurons, Encode, Timing, Firing

By Andrew Fairless on August 4, 2021July 12, 2021

https://www.quantamagazine.org/a-new-kind-of-information-coding-seen-in-the-human-brain-20210707/ neuroscienceNeurons Unexpectedly Encode Information in the Timing of Their FiringElena RenkenContributing WriterJuly 7, 2021 “A temporal pattern of activity observed in human brains for the first time may explainContinue readingWhat I Read: Neurons, Encode, Timing, Firing

What I Read: Gradient Pseudo-Swap

By Andrew Fairless on August 3, 2021July 12, 2021

https://deepnote.com/@martin-molnar/Gradient-Pseudo-Swap-F2u_aTbqTOisNYCH_JORwg Martin MolnarGradient Pseudo-Swap “When we have layers in a neural network we want to train with gradient descent, but those layers don’t have smooth gradients that can be used,Continue readingWhat I Read: Gradient Pseudo-Swap

Year: 2021