Data Science Papers for Spring 2020

The world of data science is rapidly evolving. Here are a few data science papers I have found interesting.

• What’s Wrong with Computational Notebooks? Pain Points, Needs, and Design Opportunities
  This paper is a study done on the usage of notebooks for data science. It cover a bunch of the negative impacts of using notebooks for data science. Deployment, setup, collaboration, and reliablity are a few of the examples.
• Quantifying the Carbon Emissions of Machine Learning
  Training a neural network can take a lot of computer processing power. This processing power comes at a cost to the environment. This paper looks at that cost and how location and type of equipment makes a difference.
• Software Engineering for Machine Learning: a case study
  This paper from Microsoft Research discusses the issues with building machine learning into software products.
• A primer in BERTology
  Bidirectional Encoder Representations from Transformers (BERT) is a language representation model for Natural Language Processing. This paper looks into the inner workings of BERT and potential research directions. Original BERT paper can be found here.
• Demonstration of QCCD trapped-ion quantum computer architecture
  Honeywell plans to build the most powerful quantum computer. This paper describes the architecture of the quantum computer.
• Software Developers Learning Machine Learning: Motivations, Hurdles, and Desires
  This paper from Google and UC San Diego discussed the hurdles and challenges of going from a traditional software developer to a machine learning enthusiast. It includes a survey of the TensorFlow.js community.
  

Other lists of papers can be found on the Data Science Papers page.