2021 – Page 17 – Andrew Fairless, Ph.D.

What I Read: Exploiting machine learning pickle files

By Andrew Fairless on April 4, 2021March 21, 2021

https://blog.trailofbits.com/2021/03/15/never-a-dill-moment-exploiting-machine-learning-pickle-files/ Never a dill moment: Exploiting machine learning pickle filesMarch 15, 2021By Evan Sultanik “we discuss the underhanded antics that can occur simply from loading an untrusted pickle file orContinue readingWhat I Read: Exploiting machine learning pickle files

What I Watch: How to Debug Your Team

By Andrew Fairless on April 3, 2021March 21, 2021

https://youtu.be/fIql6Kz4GIQ How to Debug Your TeamJan 4, 2021InfoQ “Lisa van Gelder tells stories about how she debugged teams at three companies… and the surprising and unintentional consequences of not givingContinue readingWhat I Watch: How to Debug Your Team

What I Read: Bayesian Hierarchical Modelling at Scale

By Andrew Fairless on April 2, 2021March 21, 2021

https://florianwilhelm.info/2020/10/bayesian_hierarchical_modelling_at_scale/ Finally! Bayesian Hierarchical Modelling at ScaleFlorian WilhelmDate Oct. 01, 2020 “In this blog post, I want to draw your attention to the somewhat dusty Bayesian Hierarchical Modelling. Modern techniquesContinue readingWhat I Read: Bayesian Hierarchical Modelling at Scale

What I Read: Causal design patterns

By Andrew Fairless on April 1, 2021March 15, 2021

https://emilyriederer.netlify.app/post/causal-design-patterns/ Causal design patterns for data analystsJan 30, 2021 “…it’s easy to do causal inference wrong. For example, attempting to control for the wrong variables can sometimes induce correlations andContinue readingWhat I Read: Causal design patterns

What I Read: Generalization in Deep Learning

By Andrew Fairless on March 31, 2021April 3, 2021

https://ai.googleblog.com/2021/03/a-new-lens-on-understanding.html A New Lens on Understanding Generalization in Deep LearningWednesday, March 10, 2021Hanie Sedghi, Google Research and Preetum Nakkiran, Harvard University “…we find that models that train quickly on infiniteContinue readingWhat I Read: Generalization in Deep Learning

What I Read: Kedro Pipelines with Airflow

By Andrew Fairless on March 30, 2021March 15, 2021

https://medium.com/quantumblack/kedro-airflow-0-4-0-orchestrating-kedro-pipelines-with-airflow-23fb1283f24d Kedro-Airflow 0.4.0 — Orchestrating Kedro Pipelines with AirflowThe Kedro team and Astronomer have released Kedro-Airflow 0.4.0 to help you develop modular, maintainable & reproducible code with orchestration superpowers!QuantumBlack, aContinue readingWhat I Read: Kedro Pipelines with Airflow

What I Read: Reducing High Cost of Training NLP Models

By Andrew Fairless on March 29, 2021April 3, 2021

https://www.asapp.com/blog/reducing-the-high-cost-of-training-nlp-models-with-sru/ Reducing the High Cost of Training NLP Models With SRU++By Tao Lei, PhDResearch Leader and Scientist at ASAPP “The Transformer architecture was proposed to accelerate model training in NLP….Continue readingWhat I Read: Reducing High Cost of Training NLP Models

What I Read: 15 common coding mistakes data scientist make

By Andrew Fairless on March 28, 2021March 7, 2021

https://towardsdatascience.com/15-common-coding-mistakes-data-scientist-make-in-python-and-how-to-fix-them-7760467498af 15 common coding mistakes data scientist make in Python (and how to fix them)Gerold CsendesDec 1, 2020 “I gradually realized in my data science career that by applying softwareContinue readingWhat I Read: 15 common coding mistakes data scientist make

What I Read: Difficulty of Graph Anonymisation

By Andrew Fairless on March 27, 2021March 7, 2021

https://www.timlrx.com/blog/tracetogether-and-the-difficulty-of-graph-anonymisation Timothy Lin@timlrxxSunday, February 7, 2021TraceTogether and the Difficulty of Graph Anonymisation “The word “anonymised data” seems to convey a certain sense of certainty that user information cannot be back-derived.Continue readingWhat I Read: Difficulty of Graph Anonymisation

What I Read: Language Model Fine-tuning

By Andrew Fairless on March 26, 2021March 7, 2021

https://ruder.io/recent-advances-lm-fine-tuning/ Recent Advances in Language Model Fine-tuningThis article provides an overview of recent methods to fine-tune large pre-trained language models.Sebastian Ruder24 Feb 2021 “While pre-training is compute-intensive, fine-tuning can beContinue readingWhat I Read: Language Model Fine-tuning

Year: 2021