Quaternion equivariant capsule networks for 3d point clouds
We present a 3D capsule module for processing point clouds that is equivariant to 3D
rotations and translations, as well as invariant to permutations of the input points. The …
rotations and translations, as well as invariant to permutations of the input points. The …
Dealing with sparse rewards in reinforcement learning
J Hare - arXiv preprint arXiv:1910.09281, 2019 - arxiv.org
Successfully navigating a complex environment to obtain a desired outcome is a difficult
task, that up to recently was believed to be capable only by humans. This perception has …
task, that up to recently was believed to be capable only by humans. This perception has …
Principled weight initialization for hypernetworks
Hypernetworks are meta neural networks that generate weights for a main neural network in
an end-to-end differentiable manner. Despite extensive applications ranging from multi-task …
an end-to-end differentiable manner. Despite extensive applications ranging from multi-task …
[PDF][PDF] Machine learning, linear algebra, and more: Is SQL all you need?
ABSTRACT SQL is the standard language for retrieving and manipulating relational data.
Although SQL is ubiquitous for simple analytical queries, it is rarely used for more complex …
Although SQL is ubiquitous for simple analytical queries, it is rarely used for more complex …
A simple and efficient tensor calculus
S Laue, M Mitterreiter, J Giesen - … of the AAAI Conference on Artificial …, 2020 - ojs.aaai.org
Computing derivatives of tensor expressions, also known as tensor calculus, is a
fundamental task in machine learning. A key concern is the efficiency of evaluating the …
fundamental task in machine learning. A key concern is the efficiency of evaluating the …
A probabilistic reformulation technique for discrete RIS optimization in wireless systems
A Pradhan, HS Dhillon - IEEE Transactions on Wireless …, 2023 - ieeexplore.ieee.org
The use of reconfigurable intelligent surfaces (RIS) can improve wireless communication by
modifying the wireless link to create virtual line-of-sight links, bypass blockages, suppress …
modifying the wireless link to create virtual line-of-sight links, bypass blockages, suppress …
Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
Solving a linear system $ Ax= b $ is a fundamental scientific computing primitive for which
numerous solvers and preconditioners have been developed. These come with parameters …
numerous solvers and preconditioners have been developed. These come with parameters …
Why capsule neural networks do not scale: Challenging the dynamic parse-tree assumption
Capsule neural networks replace simple, scalar-valued neurons with vector-valued
capsules. They are motivated by the pattern recognition system in the human brain, where …
capsules. They are motivated by the pattern recognition system in the human brain, where …
Partial information decomposition via deficiency for multivariate gaussians
P Venkatesh, G Schamberg - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
Bivariate partial information decompositions (PIDs) characterize how the information in a"
message" random variable is decomposed between two" constituent" random variables in …
message" random variable is decomposed between two" constituent" random variables in …