Publications by Sigrid Keydana
Using torch modules
Initially, we started learning about torch basics by coding a simple neural network from scratch, making use of just a single of torch’s features: tensors. Then, we immensely simplified the task, replacing manual backpropagation with autograd. Today, we modularize the network – in both the habitual and a very literal sense: Low-level matrix o...
4603 sym R (4130 sym/16 pcs)
Optimizers in torch
This is the fourth and last installment in a series introducing torch basics. Initially, we focused on tensors. To illustrate their power, we coded a complete (if toy-size) neural network from scratch. We didn’t make use of any of torch’s higher-level capabilities – not even autograd, its automatic-differentiation feature. This changed in t...
4122 sym R (3175 sym/8 pcs)
Classifying images with torch
In recent posts, we’ve been exploring essential torch functionality: tensors, the sine qua non of every deep learning framework; autograd, torch’s implementation of reverse-mode automatic differentiation; modules, composable building blocks of neural networks; and optimizers, the – well – optimization algorithms that torch provides. But w...
9218 sym R (7767 sym/25 pcs) 6 img
torch for tabular data
Machine learning on image-like data can be many things: fun (dogs vs. cats), societally useful (medical imaging), or societally harmful (surveillance). In comparison, tabular data – the bread and butter of data science – may seem more mundane. What’s more, if you’re particularly interested in deep learning (DL), and looking for the extra...
8600 sym R (8056 sym/13 pcs) 2 img 1 tbl
Brain image segmentation with torch
When what is not enough True, sometimes it’s vital to distinguish between different kinds of objects. Is that a car speeding towards me, in which case I’d better jump out of the way? Or is it a huge Doberman (in which case I’d probably do the same)? Often in real life though, instead of coarse-grained classification, what is needed is fine-...
9417 sym R (13197 sym/18 pcs) 10 img
Convolutional LSTM for spatial forecasting
This post is the first in a loose series exploring forecasting of spatially-determined data over time. By spatially-determined I mean that whatever the quantities we’re trying to predict – be they univariate or multivariate time series, of spatial dimensionality or not – the input data are given on a spatial grid. For example, the input cou...
15357 sym R (14411 sym/20 pcs) 2 tbl
Forecasting El Niño-Southern Oscillation (ENSO)
Today, we use the convLSTM introduced in a previous post to predict El Niño-Southern Oscillation (ENSO). El Niño, la Niña ENSO refers to a changing pattern of sea surface temperatures and sea-level pressures occurring in the equatorial Pacific. From its three overall states, probably the best-known is El Niño. El Niño occurs when surface wat...
13668 sym R (85688 sym/28 pcs) 4 img
torch, tidymodels, and high-energy physics
So what’s with the clickbait (high-energy physics)? Well, it’s not just clickbait. To showcase TabNet, we will be using the Higgs dataset (Baldi, Sadowski, and Whiteson (2014)), available at UCI Machine Learning Repository. I don’t know about you, but I always enjoy using datasets that motivate me to learn more about things. But first, let�...
14784 sym R (6869 sym/17 pcs) 6 img
First mlverse survey results – software, applications, and beyond
Thank you everyone who participated in our first mlverse survey! Wait: What even is the mlverse? The mlverse originated as an abbreviation of multiverse1, which, on its part, came into being as an intended allusion to the well-known tidyverse. As such, although mlverse software aims for seamless interoperability with the tidyverse, or even integr...
21387 sym 26 img
Introductory time series forecasting with torch
This is the first post in a series introducing time-series forecasting with torch. It does assume some prior experience with torch and/or deep learning. But as far as time series are concerned, it starts right from the beginning, using recurrent neural networks (GRU or LSTM) to predict how something develops in time. In this post, we build a netw...
13228 sym R (10211 sym/22 pcs) 14 img