Getting familiar with torch tensors
In this first installment of a four-part miniseries, we present the main things you will want to know about torch tensors. As an illustrative example, we’ll code a simple neural...continue reading.
In this first installment of a four-part miniseries, we present the main things you will want to know about torch tensors. As an illustrative example, we’ll code a simple neural...continue reading.
Sparklyr 1.4 is now available! This release comes with delightful new features such as weighted sampling and tidyr verbs support for Spark dataframes, robust scaler for standardizing data based on...continue reading.
Today, we are excited to introduce torch, an R package that allows you to use PyTorch-like functionality natively from R. No Python installation is required: torch is built directly on...continue reading.
We are pleased to announce that sparklyr.flint, a sparklyr extension for analyzing time series at scale with Flint, is now available on CRAN. Flint is an open-source library for working...continue reading.
A few weeks ago, we showed how to forecast chaotic dynamical systems with deep learning, augmented by a custom constraint derived from domain-specific insight. Global weather is a chaotic system,...continue reading.
This post explores how to train large datasets with TensorFlow and R. Specifically, we present how to download and repartition ImageNet, followed by training ImageNet across multiple GPUs in distributed...continue reading.
A couple of months ago, Amazon, Facebook, Microsoft, and other contributors initiated a challenge consisting of telling apart real and AI-generated (“fake”) videos. We show how to approach this challenge...continue reading.
In the last part of this mini-series on forecasting with false nearest neighbors (FNN) loss, we replace the LSTM autoencoder from the previous post by a convolutional VAE, resulting in...continue reading.
Nowadays, Microsoft, Google, Facebook, and OpenAI are sharing lots of state-of-the-art models in the field of Natural Language Processing. However, fewer materials exist how to use these models from R....continue reading.
Storing SQL Server database files in Azure blob storage is a great solution for all the databases that are often migrated between instances, servers, virtual machines, or would have been...continue reading.
In this blog post, Jannik will show you how to deploy your machine learning models as a REST API and how to make requests to the API from within your...continue reading.
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.continue reading.
In a recent post, we showed how an LSTM autoencoder, regularized by false nearest neighbors (FNN) loss, can be used to reconstruct the attractor of a nonlinear, chaotic dynamical system....continue reading.
Sparklyr 1.3 is now available, featuring exciting new functionalities such as integration of Spark higher-order functions and data import/export in Avro and in user-defined serialization formats.continue reading.
Are you confused by Bayesian statistics? If you understand Ridge regression, one of the most common Bayesian models is within your reach! This post gives a brief intro to Bayesian...continue reading.
This talk was presented virtually at eRum 2020 by Appsilon engineer Krystian Igras. Here is a direct link to the video. Why Should We Explain Black Box ML Models? A...continue reading.
Watch me answer 59 of YOUR scikit-learn questions in 90 minutes! Topic include class imbalance, preprocessing, categorical features, data leakage, and more…continue reading.
This talk was presented virtually at eRum 2020 and useR 2020. Learn more about Appsilon‘s ML wildlife preservation project here. Yes, R programmers can make machine learning models, too! In...continue reading.
In nonlinear dynamics, when the state space is thought to be multidimensional but all we have for data is just a univariate time series, one may attempt to reconstruct the...continue reading.
PixelCNN is a deep learning architecture – or bundle of architectures – designed to generate highly realistic-looking images. To use it, no reverse-engineering of arXiv papers or search for reference...continue reading.