A pit stop: DCGANs using PyTorch

Unravelling diffusion models using PyTorch

A gentle explanation of self-attention as used in Transformers and how to implement it in PyTorch and Torch for R.

An overly annotated walkthrough and implementation of a vision transformer using PyTorch.

WIP: This short code walkthrough illustrates how one can implement various variations of UNets from scratch using Pytorch.

Getting started with R7

Demonstrates how to use R to create directories and copy/move files about.

This chapter introduces readers to the discipline of signal processing and presents several applications of digital signal processing, including musical sound processing, echo generation, echo removal, and how to use R to perform such computations.

preprocess and load datasets with torch Dataset and Dataloader

Experimenting with Torch from R

Exploring how to leverage Transformers from R

A document exploring modal spatial interaction modelss

Getting started with racing methods for efficient model evaluation.

This post shows how to leverage some of the customisable, pretrained models in Azure, through R, to do some cool (and eventually useful) AI workloads.

password protected HTML files

Diving deeper into SIMs using R

Experimenting with boosted trees stacked with linear models.

Trying to get my footing in SIMs

Finally trying to get my footing in Predictive modeling for text using the book: Supervised Machine Learning for Text Analysis in R

This module is a build-up to a previous tutorial that focused on classification using Tidymodels. In this module, we hit the ground running with unsupervised learning. We use the `Tidymodels` framework in `R` and other amazing packages to train and evaluate K-Means clustering as well as Hierarchical clustering.

This module is a build-up to a previous tutorial that focused on regression using Tidymodels. In this module, we go a step further and start building classification models. We use the `Tidymodels` framework in `R` to train and evaluate classification models using different algorithms, do some data preprocessing, tune some hyperparameters and make better predictions.

Finally trying to get my footing in Predictive modeling for text using the book: Supervised Machine Learning for Text Analysis in R

This module is a build-up to a previous tutorial that focused on exploring and analyzing data using R. In this module, we go a step further and start building regression models. We use the `Tidymodels` framework in `R` to train and evaluate regression models using different algorithms, do some data preprocessing, tune some hyperparameters and make better predictions.

Unsurprisingly, the role of a data scientist primarily involves exploring and analyzing data. The results of this analysis might form the basis of a report or a machine learning model; but it all begins with data. In this module, we learn how to use R to explore, visualize, and manipulate data. Data exploration is at the core of data science, and is a key element in data analysis and machine learning.

This post is a gentle introduction to the use of R and Arduino to control peripherals such as LEDs and servo motors. It demonstrates how a communication link can be set up between the two which opens up the possibility of controlling hardware right from R!

In this post, we analyze a speech signal in the time and frequency domain whilst covering fundamental concepts in DSP using R.

This notebook is an R version of the Python notebook used by Laurence Moroney, a Developer Advocate at Google working on Artificial Intelligence, for the eighth YouTube episode of Machine Learning Foundations: Ep 8- Tokenization for Natural Language Processing.

This is just the R community expressing our best wishes to Pablo.

This notebook is an R version of the Python notebook used by Laurence Moroney, a Developer Advocate at Google working on Artificial Intelligence, for the seventh YouTube episode of Machine Learning Foundations: Ep 7- Image augmentation and overfitting.

This Notebook tries to explain the concepts of Convolutional Neural Networks and how they extract features from an image before feeding the output to the Densely Connected layers. Co-authored with Ian Muchiri.

This notebook is an R version of the Python notebook used by Laurence Moroney, a Developer Advocate at Google working on Artificial Intelligence, for the sixth YouTube session: Machine Learning Foundations: Ep 6- Convolutional cats and dogs

This notebook is an R version of the Python notebook used by Laurence Moroney, a Developer Advocate at Google working on Artificial Intelligence, for the fifth YouTube session: Machine Learning Foundations: Ep 5- Classifying real-world images.

This notebook is an R version of the Python notebook used by Laurence Moroney, a Developer Advocate at Google working on Artificial Intelligence, for the fourth YouTube session: Machine Learning Foundations: Ep #4 - Coding with Convolutional Neural Networks

This notebook is an R version of the Python notebook used by Laurence Moroney, a Developer Advocate at Google working on Artificial Intelligence, for the second YouTube session: Machine Learning Foundations: Ep 2- First steps in computer vision.

This notebook is an R version of the Python notebook used by Laurence Moroney, a Developer Advocate at Google working on Artificial Intelligence, for the first YouTube session: Machine Learning Foundations: Ep #1 - What is ML?

This session aims at demystifying the data wrangling process from importing data to some basic transformation using packages in the Tidyverse.