Digests » 116
this week's favorite
interviewer: Great, great. And are you OK with writing code on the whiteboard?
Reinforcement learning (RL) provides exciting opportunities for game development, as highlighted in our recently announced Project Paidia—a research collaboration between our Game Intelligence group at Microsoft Research Cambridge and game developer Ninja Theory.
In this article, we start off simple with Linear Regression. It is a well-known algorithm and it is the basics of this vast field. Linear Regression is, sort of, the root of it all. We will address theory and math behind it and show how we can implement this simple algorithm using several different technologies.
I approached the problem more so as a series of experiments as opposed to an actual attempt to get the lowest MSE on the test set. My approach is pretty simple. First calculate the optical flow field of successive images, then train a CNN on these optical flow fields to predict speed.
GPT-3 is the largest natural language processing (NLP) transformer released to date, eclipsing the previous record, Microsoft Research’s Turing-NLG at 17B parameters, by about 10 times. Unsurprisingly there has been plenty of excitement surrounding the model, and, given the plethora of GPT-3 demonstrations on Twitter and elsewhere, OpenAI has apparently been pretty accommodating in providing beta access to the new API. This has resulted in an explosion of demos: some good, some bad, all interesting. Some of these demos are now being touted as soon-to-be-released products, and in some cases may actually be useful. One thing’s for certain, NLP has come a long way from the days when naming guinea pigs or writing nonsensical sci-fi scripts were killer apps.