2021 – Page 10 – Andrew Fairless, Ph.D.

What I Read: Same or Different? The Question Flummoxes Neural Networks

By Andrew Fairless on July 19, 2021July 2, 2021

https://www.quantamagazine.org/same-or-different-ai-cant-tell-20210623/ Same or Different? The Question Flummoxes Neural Networks.John PavlusContributing WriterJune 23, 2021 “One of the most powerful classes of artificial intelligence systems, known as convolutional neural networks or CNNs…Continue readingWhat I Read: Same or Different? The Question Flummoxes Neural Networks

What I Read: Do Multi-Task Learning Intelligently

By Andrew Fairless on July 15, 2021July 2, 2021

https://thegradient.pub/how-to-do-multi-task-learning-intelligently/ How to Do Multi-Task Learning Intelligently22.Jun.2021 “Traditionally, a single machine learning model is devoted to one task… There are some advantages, however, to training models to make multiple kindsContinue readingWhat I Read: Do Multi-Task Learning Intelligently

What I Read: Tabular Data, Deep Learning is Not All You Need

By Andrew Fairless on July 14, 2021June 22, 2021

https://arxiv.org/abs/2106.03253v1 Tabular Data: Deep Learning is Not All You NeedRavid Shwartz-Ziv, Amitai Armon “Our study shows that XGBoost outperforms these deep models across the datasets, including datasets used in theContinue readingWhat I Read: Tabular Data, Deep Learning is Not All You Need

What I Read: How troubleshoot memory problems in Python

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

https://innovation.alteryx.com/how-to-troubleshoot-memory-problems-in-python/ How to troubleshoot memory problems in PythonFreddy BoultonJun 16, 2021 “Memory problems are hard to diagnose and fix in general, but I’d argue it’s even harder in Python. Python’sContinue readingWhat I Read: How troubleshoot memory problems in Python

What I Read: Dask vs Vaex

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

https://vaex.io/blog/dask-vs-vaex-a-qualitative-comparison Dask vs Vaex – a qualitative comparisonJovan VeljanoskiJune 15, 2021 “Vaex is flat out the fastest and most memory efficient Python DataFrame library out there…. There are still plentyContinue readingWhat I Read: Dask vs Vaex

What I Read: null hypothesis significance testing falls apart when considering replications

By Andrew Fairless on July 8, 2021June 22, 2021

https://statmodeling.stat.columbia.edu/2021/06/17/guttman-points-out-another-problem-with-null-hypothesis-significance-testing-it-falls-apart-when-considering-replications/ Guttman points out another problem with null hypothesis significance testing: It falls apart when considering replications.by Andrew Gelman17 June 2021, 9:22 am “… another problem with null hypothesis significanceContinue readingWhat I Read: null hypothesis significance testing falls apart when considering replications

What I Read: Five types of thinking

By Andrew Fairless on July 7, 2021June 22, 2021

https://towardsdatascience.com/five-types-of-thinking-for-a-high-performing-data-scientist-8ab70d70c23b?gi=772956cb941c Thinking about thinking (Part 1)Five types of thinking for a high performing data scientistFrom mental models to computational thinkingAnand S RaoApr 25 “As data scientists, we have to understandContinue readingWhat I Read: Five types of thinking

What I Read: What is a Data Mesh?

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

https://cnr.sh/essays/what-the-heck-data-mesh What the Heck is a Data Mesh?!Chris Riccomini on June 8, 2021 “Yet, organizations don’t think of data as a product…. It would be madness to propose centralizing allContinue readingWhat I Read: What is a Data Mesh?

What I Read: Data Scientists Need to Know How to Code

By Andrew Fairless on July 5, 2021June 22, 2021

https://www.kdnuggets.com/2021/06/data-scientists-need-know-code.html Data Scientists, You Need to Know How to CodeBy Tyler Folkman, Head of AI at Branded Entertainment Network “You write tons of code in Jupyter notebooks, hundreds of lines,Continue readingWhat I Read: Data Scientists Need to Know How to Code

What I Read: Contrastive Representation Learning

By Andrew Fairless on July 1, 2021June 7, 2021

https://lilianweng.github.io/lil-log/2021/05/31/contrastive-representation-learning.html Contrastive Representation Learningby Lilian WengMay 31, 2021 “The goal of contrastive representation learning is to learn such an embedding space in which similar sample pairs stay close to eachContinue readingWhat I Read: Contrastive Representation Learning

Year: 2021