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

What I Read: definitive guide to AI monitoring

By Andrew Fairless on March 7, 2021March 7, 2021

https://towardsdatascience.com/the-definitive-guide-to-ai-monitoring-2427812cc1b?gi=d1344496bc82 The definitive guide to AI monitoringLearning from our work creating production visibility for teams across deep learning and machine learning use casesYotam OrenNov 3, 2020 “AI teams across verticalsContinue readingWhat I Read: definitive guide to AI monitoring

What I Read: Deploying Machine Learning, a Survey of Case Studies

By Andrew Fairless on February 23, 2021February 3, 2021

https://arxiv.org/abs/2011.09926 Challenges in Deploying Machine Learning: a Survey of Case StudiesAndrei Paleyes, Raoul-Gabriel Urma, Neil D. Lawrence “This survey reviews published reports of deploying machine learning solutions in a varietyContinue readingWhat I Read: Deploying Machine Learning, a Survey of Case Studies

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: Explainable AI, 2-Stage Approach

By Andrew Fairless on February 5, 2021January 10, 2021

https://www.kdnuggets.com/2020/10/explaining-explainable-ai.html Explaining the Explainable AI: A 2-Stage ApproachBy Amit Dhurandhar, Research Scientist at IBM. “XAI is primarily concerned with understanding or interpreting the decisions made by these opaque or black-boxContinue readingWhat I Read: Explainable AI, 2-Stage Approach

What I Read: “Less than one”-shot learning

By Andrew Fairless on February 4, 2021January 10, 2021

https://www.technologyreview.com/2020/10/16/1010566/ai-machine-learning-with-tiny-data/ Artificial intelligence/Machine learningA radical new technique lets AI learn with practically no data“Less than one”-shot learning can teach a model to identify more objects than the number of examplesContinue readingWhat I Read: “Less than one”-shot learning

What I Read: AI Can Help Patients If Doctors Understand It

By Andrew Fairless on January 27, 2021January 1, 2021

https://www.wired.com/story/ai-help-patients-doctors-understand/ Tom SimoniteBusiness10.02.2020 08:00 AMAI Can Help Patients—but Only If Doctors Understand It Algorithms can help diagnose a growing range of health problems, but humans need to be trained toContinue readingWhat I Read: AI Can Help Patients If Doctors Understand It

What I Read: Maintaining Machine Learning in Production

By Andrew Fairless on January 19, 2021December 27, 2020

https://eugeneyan.com/writing/practical-guide-to-maintaining-machine-learning/ A Practical Guide to Maintaining Machine Learning in Production “This follow-up will share some practices I’ve found useful to maintaining machine learning in production. They are: Monitor Training andContinue readingWhat I Read: Maintaining Machine Learning in Production

What I Read: making machine learning actually useful

By Andrew Fairless on January 5, 2021December 22, 2020

https://www.shreya-shankar.com/making-ml-work/ Shreya ShankarReflecting on a year of making machine learning actually usefulJune 29, 2020 in #machine learning · 11 min read “…ML research as a field puts too much emphasisContinue readingWhat I Read: making machine learning actually useful

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

Tag: interpretability