March 2021 – Andrew Fairless, Ph.D.

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

What I Read: Python Concurrency

By Andrew Fairless on March 25, 2021March 7, 2021

https://python.hamel.dev/concurrency/ Python NotesPython Concurrency: The Tricky Bits2020-02-05 concurrency An exploration of threads, processes, and coroutines in Python, with interesting examples that illuminate the differences between each.“I’ve found many data scientistsContinue readingWhat I Read: Python Concurrency

What I Read: Data Quality Management

By Andrew Fairless on March 24, 2021March 7, 2021

https://medium.com/dataseries/inside-the-architecture-powering-data-quality-management-at-uber-543d5e00ad19 Inside the Architecture Powering Data Quality Management at UberData Quality Monitor implements novel statistical methods for anomaly detection and quality management in large data infrastructures.Jesus RodriguezFeb 10 “Data qualityContinue readingWhat I Read: Data Quality Management

What I Read: Neural Nets, How Brains Learn

By Andrew Fairless on March 23, 2021March 7, 2021

https://www.quantamagazine.org/artificial-neural-nets-finally-yield-clues-to-how-brains-learn-20210218/ Artificial Neural Nets Finally Yield Clues to How Brains LearnAnil AnanthaswamyContributing WriterFebruary 18, 2021 “The learning algorithm that enables the runaway success of deep neural networks doesn’t work inContinue readingWhat I Read: Neural Nets, How Brains Learn

What I Read: Continual Learning, Amnesia, Neural Networks

By Andrew Fairless on March 22, 2021March 7, 2021

https://medium.com/dataseries/ibm-uses-continual-learning-to-avoid-the-amnesia-problem-in-neural-networks-ae8241e1f3a3 IBM Uses Continual Learning to Avoid The Amnesia Problem in Neural NetworksUsing continual learning might avoid the famous catastrophic forgetting problem in neural networks.Jesus RodriguezJan 25 “Building neural networksContinue readingWhat I Read: Continual Learning, Amnesia, Neural Networks

Month: March 2021