-
Serving models at scale with LoRA
This blog post describes how we use LoRA to serve hundreds of models without breaking the bank on our GPU spend.
-
Comparing classifiers via bootstrapped confidence intervals
If we have two classifiers to perform the same task, how can we tell, which one is better? We could, of course, compare their accuracy: If the first classifier has an accuracy of 70% and the second classifier has an accuracy of 72%, then clearly the second classifier better, right? Well, maybe…
-
What’s Hidden in a Randomly Weighted Neural Network?
Usually training a neural network means finding values for weights such that the network performs well on a given task, while keeping the network architecture fixed. The paper What’s Hidden in a Randomly Weighted Neural Network? investigates what happens if we swap the roles: we fix the values of weights and look for subnetworks in a given network that perform well on a given task; in other words, we optimise the network architecture while keeping weights fixed.
-
Representation Learning with Contrastive Predictive Coding
Contrastive Predictive Coding is an unsupervised learning approach for learning useful representations from high-dimensional data.
-
Going Deeper with Image Transformers
Our journey along the ImageNet leaderboard next takes us to 33rd place and the paper Going Deeper with Image Transformers by Touvron et al., 2021. In this paper they look at tweaks to the transformer architecture that allow them (a) to increase accuracy without needing external data beyond the ImageNet training set and (b) to train deeper transformer models.