The Perceptron stands as one of the most basic building blocks for creating neural networks, including more advanced structures like deep networks and their variants. Originally developed in the late...continue reading.
Unless you’ve been living in cave somewhere in remote Eurasia, you should know that deep learning is very popular, and very powerful. A variety of tools from self driving cars...continue reading.
Hugging Face rapidly became a very popular platform to build, share and collaborate on deep learning applications. We have worked on integrating the torch for R ecosystem with Hugging Face...continue reading.
Obviously, AI taken off in the last year in ways that were hard for most people to predict. AI went from being a somewhat niche technical subject that nerdy guys...continue reading.
LoRA (Low Rank Adaptation) is a new technique for fine-tuning deep learning models that works by reducing the number of trainable parameters and enables efficient task switching. In this blog...continue reading.
A couple of days ago, I wrote a blog post about how GPT writes bad Pandas code. If you’ve been reading at the blog for a while, you’ve probably realized...continue reading.
This is a high-level, introductory article about Large Language Models (LLMs), the core technology that enables the much-en-vogue chatbots as well as other Natural Language Processing (NLP) applications. It is...continue reading.
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.
Announcing safetensors, a new R package allowing for reading and writing files in the safetensors format.continue reading.
AI is turning the tech world upside-down right now. With the release of large-language systems like Chat-GPT and various coding copilots, many people are questioning the value of a tech...continue reading.
torch v0.11.0 is now on CRAN. This release features much-enhanced support for executing JIT operations. We also amended loading of model parameters, and added a few quality-of-life improvements, like support...continue reading.
Implementation and walk-through of LLaMA, a Large Language Model, in R, with TensorFlow and Keras.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.
For years, people have been talking about the era of “big data.” The data deluge. As early as 2010, The Economist wrote about how “quantity of information in the world...continue reading.
luz v0.4.0 is now on CRAN. This release adds support for training models on ARM Mac GPUs, reduces the overhead of using luz, and makes it easier to checkpoint and...continue reading.
torch v0.10.0 is now on CRAN. This version upgraded the underlying LibTorch to 1.13.1, and added support for Automatic Mixed Precision. As an experimental feature, we now also support pre-built...continue reading.
Currently, in generative deep learning, no other approach seems to outperform the family of diffusion models. Would you like to try for yourself? If so, our torch implementation of de-noising...continue reading.
I’ll never forget what my manager said to me. “Do you need me to break down some doors? Do you need me to flip over some tables?” He was talking...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.
With all of the buzz around the word “Machine Learning” in the world of business today, it has become increasingly difficult to determine what it actually means and how it...continue reading.
