Software
People
Events
Resources
Blog
About

Other

Concepts

Showing of

Understanding LoRA with a minimal example

Understanding LoRA with a minimal example

Understanding LoRA with a minimal example

Understanding LoRA with a minimal example

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 post we will talk about the key ideas behind LoRA in a very minimal torch example

Machine Learning Best Practices Ai Torch Concepts

What are Large Language Models? What are they not?

What are Large Language Models? What are they not?

What are Large Language Models? What are they not?

What are Large Language Models? What are they not?

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 directed at a general audience, possibly with some technical and/or scientific background, but no knowledge is assumed of either deep learning or NLP. Having looked at major model ingredients, training workflow, and mechanics of output generation, we also talk about what these models are not

Best Practices Artificial Intelligence Ai Meta Concepts Natural Language Processing

Group-equivariant neural networks with escnn

Group-equivariant neural networks with escnn

Group-equivariant neural networks with escnn

Group-equivariant neural networks with escnn

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 mathematical concepts, the library’s key actors, and essential library use

Machine Learning Best Practices Ai Torch Concepts Image Recognition Image Processing

Deep Learning and Scientific Computing with R torch: the book

Deep Learning and Scientific Computing with R torch: the book

Deep Learning and Scientific Computing with R torch: the book

Deep Learning and Scientific Computing with R torch: the book

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. From there, it moves on to various deep-learning use cases. Finally, it shows how to use torch for more general topics, such as matrix computations and the Fourier Transform

Machine Learning Best Practices Ai Torch Meta Concepts Packages Releases

Field of wheat

Field of wheat

Field of wheat

Upside down, a cat’s still a cat: Evolving image recognition with Geometric Deep Learning

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 topic of Geometric Deep Learning, a principled, math-driven approach to neural networks that has consistently been rising in scope and impact

Machine Learning Best Practices Ai Torch Spatial Data Concepts

Wavelet Transform - with torch

Wavelet Transform - with torch

Wavelet Transform - with torch

Wavelet Transform - with torch

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 very first introduction to wavelets, suitable for readers that have not encountered it before. At the same time, it provides useful starter code, showing an (extensible) way to perform wavelet analysis in torch. It is an excerpt from the corresponding chapter in the forthcoming book, Deep Learning and Scientific Computing with R torch, to be published by CRC Press

Machine Learning Best Practices Ai Torch Concepts

Discrete Fourier Transform - with torch

Discrete Fourier Transform - with torch

Discrete Fourier Transform - with torch

Discrete Fourier Transform - with torch

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 half-dozen lines of code. Even if in the end, you’re just going to call torch’s built-in functions directly, it helps to understand, and be able to reproduce in code, the ideas that underlie the magic. This post is an excerpt from the forthcoming book, Deep Learning and Scientific Computing with R torch, to be published by CRC Press

Machine Learning Best Practices Ai Torch Concepts

Five ways to do least squares (with torch)

Five ways to do least squares (with torch)

Five ways to do least squares (with torch)

Five ways to do least squares (with torch)

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 forthcoming book, Deep Learning and Scientific Computing with R torch, to be published by CRC Press

Machine Learning Best Practices Ai Torch Concepts Tabular Data

Beyond alchemy: A first look at geometric deep learning

Beyond alchemy: A first look at geometric deep learning

Beyond alchemy: A first look at geometric deep learning

Beyond alchemy: A first look at geometric deep learning

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 arise in some physical domain. A neural network that well matches the domain will preserve as many invariances as possible. In this post, we present a very conceptual, high-level overview, and highlight a few applications

Best Practices Ai Concepts Meta

Starting to think about AI Fairness

Starting to think about AI Fairness

Starting to think about AI Fairness

Starting to think about AI Fairness

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 last not least the impression that everyone else seems to know what they’re talking about. This text hopes to counteract some of that confusion by starting from a common-sense approach of contrasting two basic positions: On the one hand, the assumption that dataset features may be taken as reflecting the underlying concepts ML practitioners are interested in; on the other, that there inevitably is a gap between concept and measurement, a gap that may be bigger or smaller depending on what is being measured. In contrasting these fundamental views, we bring together concepts from ML, legal science, and political philosophy

Best Practices Ai Concepts Meta Society

Parallelized sampling using exponential variates

Parallelized sampling using exponential variates

Parallelized sampling using exponential variates

Parallelized sampling using exponential variates

How can the seemingly iterative process of weighted sampling without replacement be transformed into something highly parallelizable? Turns out a well-known technique based on exponential variates accomplishes exactly that

Best Practices MLOps and Admin Ai Concepts Distributed Computing

Infinite surprise - the iridescent personality of Kullback-Leibler divergence

Infinite surprise - the iridescent personality of Kullback-Leibler divergence

Infinite surprise - the iridescent personality of Kullback-Leibler divergence

Infinite surprise - the iridescent personality of Kullback-Leibler divergence

Kullback-Leibler divergence is not just used to train variational autoencoders or Bayesian networks (and not just a hard-to-pronounce thing). It is a fundamental concept in information theory, put to use in a vast range of applications. Most interestingly, it’s not always about constraint, regularization or compression. Quite on the contrary, sometimes it is about novelty, discovery and surprise

Machine Learning Best Practices Ai Probabilistic Machine Learning Probabilistic Deep Learning Concepts

NumPy-style broadcasting for R TensorFlow users

NumPy-style broadcasting for R TensorFlow users

NumPy-style broadcasting for R TensorFlow users

NumPy-style broadcasting for R TensorFlow users

Broadcasting, as done by Python’s scientific computing library NumPy, involves dynamically extending shapes so that arrays of different sizes may be passed to operations that expect conformity - such as adding or multiplying elementwise. In NumPy, the way broadcasting works is specified exactly; the same rules apply to TensorFlow operations. For anyone who finds herself, occasionally, consulting Python code, this post strives to explain

keras3 Machine Learning Best Practices Ai TensorFlow Keras Concepts

On leapfrogs, crashing satellites, and going nuts: A very first conceptual introduction to Hamiltonian Monte Carlo

On leapfrogs, crashing satellites, and going nuts: A very first conceptual introduction to Hamiltonian Monte Carlo

On leapfrogs, crashing satellites, and going nuts: A very first conceptual introduction to Hamiltonian Monte Carlo

On leapfrogs, crashing satellites, and going nuts: A very first conceptual introduction to Hamiltonian Monte Carlo

TensorFlow Probability, and its R wrapper tfprobability, provide Markov Chain Monte Carlo (MCMC) methods that were used in a number of recent posts on this blog. These posts were directed to users already comfortable with the method, and terminology, per se, which readers mainly interested in deep learning won’t necessarily be. Here we try to make up leeway, introducing Hamitonian Monte Carlo (HMC) as well as a few often-heard “buzzwords” accompanying it, always striving to keep in mind what it is all “for”

tfprobability Best Practices Ai Bayesian Modeling Concepts

So, how come we can use TensorFlow from R?

So, how come we can use TensorFlow from R?

So, how come we can use TensorFlow from R?

So, how come we can use TensorFlow from R?

Have you ever wondered why you can call TensorFlow - mostly known as a Python framework - from R? If not - that’s how it should be, as the R packages keras and tensorflow aim to make this process as transparent as possible to the user. But for them to be those helpful genies, someone else first has to tame the Python

keras3 Machine Learning Best Practices Ai TensorFlow Keras Meta Concepts

Adding uncertainty estimates to Keras models with tfprobability

Adding uncertainty estimates to Keras models with tfprobability

Adding uncertainty estimates to Keras models with tfprobability

Adding uncertainty estimates to Keras models with tfprobability

As of today, there is no mainstream road to obtaining uncertainty estimates from neural networks. All that can be said is that, normally, approaches tend to be Bayesian in spirit, involving some way of putting a prior over model weights. This holds true as well for the method presented in this post: We show how to use tfprobability, the R interface to TensorFlow Probability, to add uncertainty estimates to a Keras model in an elegant and conceptually plausible way

keras3 Machine Learning Best Practices Ai Probabilistic Machine Learning Probabilistic Deep Learning TensorFlow Keras Concepts

Getting into the flow: Bijectors in TensorFlow Probability

Getting into the flow: Bijectors in TensorFlow Probability

Getting into the flow: Bijectors in TensorFlow Probability

Getting into the flow: Bijectors in TensorFlow Probability

Normalizing flows are one of the lesser known, yet fascinating and successful architectures in unsupervised deep learning. In this post we provide a basic introduction to flows using tfprobability, an R wrapper to TensorFlow Probability. Upcoming posts will build on this, using more complex flows on more complex data

keras3 Machine Learning Best Practices Ai Probabilistic Machine Learning Probabilistic Deep Learning TensorFlow Keras Concepts Generative Models

Math, code, concepts: A third road to deep learning

Math, code, concepts: A third road to deep learning

Math, code, concepts: A third road to deep learning

Math, code, concepts: A third road to deep learning

Not everybody who wants to get into deep learning has a strong background in math or programming. This post elaborates on a concepts-driven, abstraction-based way to learn what it’s all about

keras3 Best Practices Ai Meta Concepts

Audio classification with Keras: Looking closer at the non-deep learning parts

Audio classification with Keras: Looking closer at the non-deep learning parts

Audio classification with Keras: Looking closer at the non-deep learning parts

Audio classification with Keras: Looking closer at the non-deep learning parts

Sometimes, deep learning is seen - and welcomed - as a way to avoid laborious preprocessing of data. However, there are cases where preprocessing of sorts does not only help improve prediction, but constitutes a fascinating topic in itself. One such case is audio classification. In this post, we build on a previous post on this blog, this time focusing on explaining some of the non-deep learning background. We then link the concepts explained to updated for near-future releases TensorFlow code

keras3 Machine Learning Best Practices Ai TensorFlow Keras Concepts Audio Processing

Winner takes all: A look at activations and cost functions

Winner takes all: A look at activations and cost functions

Winner takes all: A look at activations and cost functions

Winner takes all: A look at activations and cost functions

Why do we use the activations we use, and how do they relate to the cost functions they tend to co-appear with? In this post we provide a conceptual introduction

keras3 Machine Learning Best Practices Ai TensorFlow Keras Concepts

Open source software and tools for data science.

Navigate

Software
People
Events
Resources
Blog
About

Resources

Posit.co
About Posit
Support
GitHub
Subscribe

Socials

GitHub Mastodon Bluesky LinkedIn YouTube RSS Feeds

2026 Posit Software, PBC. All rights reserved.

Privacy Code of Conduct

Filter by Type

|

Software

(0)

People

(0)

Events

(0)

Resources

(0)

Blog

(0)

Other

(0)

Searching...

Type to search

No results found

↑↓ Navigate

↵ Select

ESC Close