Ask Slater Is it possible to learn without data (or at least one or two samples)—like humans—in AI? May 26, 2018 by jeremystinson Humans do not learn without data, but as you’ve said, they can often learn with very small amounts of data. This is an extremely active area of research typically referred to as “one-shot learning” (learning from one example) or even “zero-shot learning” (learning from zero examples and just the name of the label you’re looking […] Read more »
Ask Slater Given a scenario, how can I identify which machine learning algorithm is best suited for this scenario? May 26, 2018 by jeremystinson You try them and see how well they work. Anything other than experimentation is guesswork. You can make very broad assertions like, “convolutional neural networks work well for image recognition”, but that doesn’t really help you determine which algorithm you should use, and even in this situation there’s no possible way to know ahead of […] Read more »
Ask Slater Is sentiment analysis in Twitter old or active research? May 25, 2018 by jeremystinson There was a particular surge in Twitter sentiment analysis in the early days of Twitter (pre-2015). It was a somewhat narrow window where this kind of research was extremely exciting because all of the traditional approaches to sentiment analysis relied on more formal corpora and these approaches broke down dramatically when applied to Twitter (as […] Read more »
Data Science Machine Learning Everything You Wanted to Know About Optimization May 17, 2018 by jeremystinson Last week our co-founder and machine learning architect, Madison May, presented at the Boston Machine Learning Meetup on various optimization methods based on trends from ICLR 2018. Video and slides below. Overview In recent years the use of adaptive momentum methods like Adam and RMSProp has become popular in reducing the sensitivity of […] Read more »
Data Science Developers Text Data Use Case Tutorials Fortnite vs. PUBG: Data Science Lessons Learned May 1, 2018 / October 9, 2025 by jeremystinson I’d like to preface this post with the fact that what I do on a day-to-day basis isn’t data science. I spend my days building the web-based tools that make using indico’s core tech easier. So when I was asked to do a small data science project and write a post about it, I truly […] Read more »
