A Real World Reinforcement Learning Research Program
We are hiring for reinforcement learning related research at all levels and all MSR labs. If you are interested, apply, talk to me at COLT or ICML, or email me. More generally though, I wanted to lay out a philosophy of research which differs from (and plausibly improves on) the current prevailing mode. Deepmind and OpenAI have popularized an... Read more
My Latent Dissatisfaction with Modern ML
It took reading Judea Pearl’s “The Book of Why”, and Jonas Peters’ mini-course on causality, for me to finally figure out why I had this lingering dissatisfaction with modern machine learning. It’s because modern machine learning (deep learning included) is most commonly used as a tool in the service... Read more
New Approximate Nearest Neighbor Benchmarks
As some of you may know, one of my side interests is approximate nearest neighbor algorithms. I’m the author of Annoy, a library with 3,500+ stars on Github as of today. It offers fast approximate search for nearest neighbors with the additional benefit that you can load data super fast... Read more
A Different Use of Time Series to Identify Seasonal Customers
I had previously written about creatively leveraging your data using segmentation to learn about a customer base.  The article is here.  In the article I mentioned utilizing any data that might be relevant.  Trying to identify customers with seasonal usage patterns was one of the variables that I mentioned that sounded interesting. ... Read more
Frontier AI: How far are we from artificial “general” intelligence, really?
Some call it “strong” AI, others “real” AI, “true” AI or artificial “general” intelligence (AGI)… whatever the term (and important nuances), there are few questions of greater importance than whether we are collectively in the process of developing generalized AI that can truly think like a human — possibly... Read more
A Look at Gary Marcus’s Deep Learning: A Critical Appraisal
There are many mixed opinions regarding the future of deep learning. Gary Marcus’s paper, “Deep Learning: A Critical Appraisal” overviews the social and more technical concerns with deep learning, and examines the possibility of it simply hitting a wall. Having only reached mainstream technology at acceptable production standards in... Read more
Requests for Research
Table of contents: Task-independent data augmentation for NLP Few-shot learning for NLP Transfer learning for NLP Multi-task learning Cross-lingual learning Task-independent architecture improvements It can be hard to find compelling topics to work on and know what questions are interesting to ask when you are just starting as a... Read more
The Six Stages of Computational Science
This is the second in a series of articles related to computational science and education.  The first article is here. The Six Stages of Computational Science When I was in grad school, I collaborated with a research group working on computational fluid dynamics.  They had accumulated a large, complex code... Read more
Let’s start with machine learning In short, machine learning algorithms are algorithms that learn (often predictive) models from data. I.e., instead of formulating “rules” manually, a machine learning algorithm will learn the model for you. So, let me give you an example to illustrate what that means! Say you... Read more
Named Entity Recognition: Milestone Models, Papers and Technologies
Named Entity Recognition: Extracting named entities from text Named Entity Recognition (NER), or entity extraction is an NLP technique which locates and classifies the named entities present in the text. Named Entity Recognition classifies the named entities into pre-defined categories such as the names of persons, organizations, locations, quantities, monetary... Read more