Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

Artificial neural networks (ANNs) inspired by biology are beginning to be widely used to
model behavioural and neural data, an approach we call 'neuroconnectionism'. ANNs have …

This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to
spatiotemporal representation learning from videos. We randomly mask out spacetime …

The two fields of machine learning and graphical causality arose and are developed
separately. However, there is, now, cross-pollination and increasing interest in both fields to …

Abstract Self-Supervised Learning (SSL) surmises that inputs and pairwise positive
relationships are enough to learn meaningful representations. Although SSL has recently …

Abstract We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-
supervised image representation learning. BYOL relies on two neural networks, referred to …

We present a large-scale study on unsupervised spatiotemporal representation learning
from videos. With a unified perspective on four recent image-based frameworks, we study a …

To date, various 3D scene understanding tasks still lack practical and generalizable pre-
trained models, primarily due to the intricate nature of 3D scene understanding tasks and …

Human observers can learn to recognize new categories of images from a handful of
examples, yet doing so with artificial ones remains an open challenge. We hypothesize that …

In this work, we perform unsupervised learning of representations by maximizing mutual
information between an input and the output of a deep neural network encoder. Importantly …