Author: Sigrid Keydana

Implementing a language model from scratch is, arguably, the best way to develop an accurate idea of how its engine works. Here, we use torch to code GPT-2, the immediate...continue reading.

Escnn, built on PyTorch, is a library that, in the spirit of Geometric Deep Learning, provides a high-level interface to designing and training group-equivariant neural networks. This post introduces important...continue reading.

Please allow us to introduce Deep Learning and Scientific Computing with R torch. Released in e-book format today, and available freely online, this book starts out by introducing torch basics....continue reading.

We code up a simple group-equivariant convolutional neural network (GCNN) that is equivariant to rotation. The world may be upside down, but the network will know.continue reading.

In this first in a series of posts on group-equivariant convolutional neural networks (GCNNs), meet the main actors — groups — and concepts (equivariance). With GCNNs, we finally revisit the...continue reading.

El Niño-Southern Oscillation (ENSO), North Atlantic Oscillation (NAO), and Arctic Oscillation (AO) are atmospheric phenomena of global impact that strongly affect people’s lives. ENSO, first and foremost, brings with it...continue reading.

torch does not have built-in functionality to do wavelet analysis. But we can efficiently implement what we need, making use of the Fast Fourier Transform (FFT). This post is a...continue reading.

About the Fourier Transform, it has been said that it is one of the greatest wonders of the universe. At the same time, it can be realized in a mere...continue reading.

Get to know torch’s linalg module, all while learning about different ways to do least-squares regression from scratch. This post is a condensed version of the corresponding chapter in the...continue reading.

Learn how to classify speech utterances with torch, making use of domain knowledge and deep learning. This post is a condensed version of the corresponding chapter in the forthcoming book,...continue reading.

Today, we want to call attention to a highly useful package in the torch ecosystem: torchopt. It extends torch by providing a set of popular optimization algorithms not available in...continue reading.

Sometimes, a software’s best feature is the one you’ve added yourself. This post shows by example why you may want to extend torch, and how to proceed. It also explains...continue reading.

For keras, the last two releases have brought important new functionality, in terms of both low-level infrastructure and workflow enhancements. This post focuses on an outstanding example of the latter...continue reading.

It’s been a while since this blog featured content about Keras for R, so you might’ve thought that the project was dormant. It’s not! In fact, Keras for R is...continue reading.

We train a model for image segmentation in R, using torch together with luz, its high-level interface. We then JIT-trace the model on example input, so as to obtain an...continue reading.

Geometric deep learning is a “program” that aspires to situate deep learning architectures and techniques in a framework of mathematical priors. The priors, such as various types of invariance, first...continue reading.

Using the torch just-in-time (JIT) compiler, it is possible to query a model trained in R from a different language, provided that language can make use of the low-level libtorch...continue reading.

The topic of AI fairness metrics is as important to society as it is confusing. Confusing it is due to a number of reasons: terminological proliferation, abundance of formulae, and...continue reading.

Today, we’re introducing luz, a high-level interface to torch that lets you train neural networks in a concise, declarative style. In some sense, it is to torch what Keras is...continue reading.