- The problem with metrics is a big problem for AI - Oct 11, 2019.
The practice of optimizing metrics is not new nor unique to AI, yet AI can be particularly efficient (even too efficient!) at doing so.
AI, Metrics, Rachel Thomas
12 NLP Researchers, Practitioners & Innovators You Should Be Following - Aug 12, 2019.
Check out this list of NLP researchers, practitioners and innovators you should be following, including academics, practitioners, developers, entrepreneurs, and more.
Influencers, Jeremy Howard, NLP, Rachel Thomas, Research, Richard Socher
Machine Learning & AI Main Developments in 2018 and Key Trends for 2019 - Dec 11, 2018.
As we bid farewell to one year and look to ring in another, KDnuggets has solicited opinions from numerous Machine Learning and AI experts as to the most important developments of 2018 and their 2019 key trend predictions.
2019 Predictions, AI, Ajit Jaokar, Andriy Burkov, Anima Anandkumar, Brandon Rohrer, Daniel Tunkelang, Machine Learning, Pedro Domingos, Rachel Thomas, Zachary Lipton
- Google’s AutoML: Cutting Through the Hype - Jul 31, 2018.
In today’s post, I want to look specifically at Google’s AutoML, a product which has received a lot of media attention, and address "What is Google's AutoML?" and more.
Automated Machine Learning, AutoML, Google, Hype, Rachel Thomas
- An Introduction to Deep Learning for Tabular Data - May 17, 2018.
This post will discuss a technique that many people don’t even realize is possible: the use of deep learning for tabular data, and in particular, the creation of embeddings for categorical variables.
Deep Learning, fast.ai, Kaggle, Neural Networks, Rachel Thomas, word2vec
- How to Make AI More Accessible - Apr 30, 2018.
I recently was a guest speaker at the Stanford AI Salon on the topic of accessiblity in AI, which included a free-ranging discussion among assembled members of the Stanford AI Lab. There were a number of interesting questions and topics, so I thought I would share a few of my answers here.
Accessibility, AI, Deep Learning, Rachel Thomas, Research
- How (and Why) to Create a Good Validation Set - Nov 24, 2017.
The definitions of training, validation, and test sets can be fairly nuanced, and the terms are sometimes inconsistently used. In the deep learning community, “test-time inference” is often used to refer to evaluating on data in production, which is not the technical definition of a test set.
Cross-validation, Datasets, Rachel Thomas, Training Data, Validation
- Credible Sources of Accurate Information About AI - Oct 9, 2017.
I want to recommend several credible sources of accurate information. Most of the writing on this list is intended to be accessible to anyone—even if you aren’t a programmer or don’t work in tech.
AI, fast.ai, Hype, Jeremy Howard, Rachel Thomas, Research, Twitter, Zeynep Tufekci