Everyone is talking about GPT-3, so, we talked about GPT-3. This seems to be the paper that started it all, “Language Models are Few-Shot Learners.” The paper is long with 75 pages, but there are 31 authors, so there are ~2.42 pages per author. That should make it easy. Probably we will only have time …
Read more→
There are 220 million speakers of Dravidian languages in the world. Most of these are speakers of Tamil or Telugu who live in South and South-Central India. That population is comparable to the English speaking population of the world, of which 360 million are native speakers. As such it seems reasonable to expect that speakers …
Read more→
We began a new thread related to ethics in AI with papers focus on papers by Buolamwini and Gebru. AI is now used routinely to make decisions that once were made by people in areas ranging from hiring to policing to social matchmaking. It seems fair to scrutinize these applications for ethics and fairness. Particularly …
Read more→
Google Research recently open sourced TaPas, a system for doing natural language queries on tabular data. The model is fully differentiable and based on BERT. We read the paper, “TAPAS: Weakly Supervised Table Parsing via Pre-training.” We ran the code from google research repo on a virtual machine and saw both the power of the …
Read more→
For this first session of 2021, we did almost a pure tutorial session. We covered BERT again, but went through the experience using using TensorFlow 2.3 and Hub on a virtual machine. Along with the tutorial, we created a small repo with requirements and some instructions.
Science is about asking questions and looking for answers. It is not a bad thing when you get exactly the answer you were expecting to exactly the question you were asking. On the other hand, it seems even better to get a completely surprising answer to a question almost but not quite the exact question …
Read more→
We are prepared to do a tutorial on setting up a C++ autotools project. Here is the autotools skeleton project with the resources to start.
On 14 January, we will begin with a tutorial on ML in a VM with GPU. I am pretty happy with the experience that i have had using TensorFlow 2.3 and Hub on a virtual machine. We have talked about the BERT paper and other language models, but I want to do a refresher with …
Read more→
For this year, we will begin offering challenge problems. These will be problems that are relevant to ecology, medicine or social welfare. For each of these problems, we will offer a data set or a way to create a data set, regression targets and baseline implementations. This year, our three problems are 1. Analyzing professional …
Read more→
This tutorial should be pretty short, and is contained in a repo. The README.md explains most of the necessary details. Additionally, this bibliography also documents the history of reading for our Reading Club.