AI-based language analysis has recently gone through a “paradigm shift” (Bommasani et al., 2021, p. 1), thanks in part to a new technique referred to as transformer language model (Vaswani et al., 2017, Liu et al., 2019). Companies, including Google, Meta, and OpenAI have released...
AlphaFold 2 paper and code is finally released. This post aims to inspire new generations of Machine Learning (ML) engineers to focus on foundational biological problems.This post is a collection of core concepts to finally grasp AlphaFold2-like stuff. Our goal is to make this...
Variations on a theme
Simple audio classification with Keras, Audio classification with Keras: Looking closer at the non-deep learning parts, Simple audio classification with torch: No, this is not the first post on this blog that introduces speech classification using deep learning. With two of...
Traditionally, datasets in Deep Learning applications such as computer vision and NLP are typically represented in the euclidean space. Recently though there is an increasing number of non-euclidean data that are represented as graphs. To this end, Graph Neural Networks (GNNs) are an effort...
Note: This post is a condensed version of a chapter from part three of the forthcoming book, Deep Learning and Scientific Computing with R torch. Part three is dedicated to scientific computation beyond deep learning. Throughout the book, I focus on the underlying concepts,...
Self-supervised learning aims to extract representation from unsupervised visual data and it’s super famous in computer vision nowadays. This article covers the SWAV method, a robust self-supervised learning paper from a mathematical perspective. To that end, we provide insights and intuitions for why this...
