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 …
R Balestriero, Y LeCun - Advances in Neural Information …, 2022 - proceedings.neurips.cc
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 …
O Henaff - International conference on machine learning, 2020 - proceedings.mlr.press
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 …