Deep Learning
MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
We propose that these limitations arise because MPNNs only pass two-body messages leading to a direct relationship between the number of layers and the expressivity of the network.
Batch Normalization Provably Avoids Rank Collapse for Randomly Initialised Deep Networks
Given the rich literature on random matrices, it is not surprising to find that the rank of the intermediate representations in unnormalized networks collapses quickly with depth.
Multi-Agent Common Knowledge Reinforcement Learning
Christian Schroeder de Witt, Jakob Foerster, Gregory Farquhar, Philip Torr, Wendelin Boehmer, Shimon Whiteson
Neural Information Processing Systems http://nips.cc/
Boundaries, drops and missed run-out chances - Ghosh's remarkable innings
Boundaries, drops and missed run-out chances - Ghosh's remarkable innings This content is not available in your location. Richa Ghosh's 94 runs off 77 balls, including 15 boundaries, helps save India's innings as they recover from 102-6 to reach 251-8 against South Africa in their ICC Women's Cricket World Cup match. Boundaries, drops and missed run-out chances - Ghosh's remarkable innings. Video, 00:03:29 Boundaries, drops and missed run-out chances - Ghosh's remarkable innings'I was asking ChatGPT is this real?' - Fraser & Tulloch on making black history. Video, 00:04:27 'I was asking ChatGPT is this real?' - Fraser & Tulloch on making black history'We've got mountains to do' - Cavallo on homophobia in football.
Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
As a result we can learn a kernel that transfers to new tasks; we call this Deep Kernel Transfer (DKT) .
Rethinking the Reverse-engineering of Trojan Triggers
Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Reverse-engineering methods can reconstruct the trigger and thus identify affected models. Existing reverse-engineering methods only consider input space constraints, e.g.,
Unsupervised Learning of Object Keypoints for Perception and Control
Tejas D. Kulkarni, Ankush Gupta, Catalin Ionescu, Sebastian Borgeaud, Malcolm Reynolds, Andrew Zisserman, Volodymyr Mnih
To this end, we introduce Transporter, a neural network architecture for discovering concise geometric object representations in terms of keypoints or image-space coordinates.