or subscribe with
Join 3,800+ readers for one email each week.
Digests » 94
this week's favorite
In this post, I’d like to summarize all my interviewing experience — from both interviewing and being interviewed — and came up with a list of 160+ theoretical data science questions.
Machine learning models have beaten humans at many games — but not Pokemon. Let’s fix that.
Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transformer, a new partially autoregressive model devised for more flexible and amenable sequence generation.
Learn how to build and deploy a machine learning application from scratch. An end-to-end tutorial on data scraping, modeling, and deployment.
Gradient Descent is one of the most fundamental optimization techniques used in Machine Learning. But what is a gradient? On what do we descent down and what do we even optimize in the first place?