English
Related papers

Related papers: Equivariant neural networks and piecewise linear r…

200 papers

Incorporating symmetry as an inductive bias into neural network architecture has led to improvements in generalization, data efficiency, and physical consistency in dynamics modeling. Methods such as CNNs or equivariant neural networks use…

Machine Learning · Computer Science 2022-06-17 Rui Wang , Robin Walters , Rose Yu

Two networks are equivalent if they produce the same output for any given input. In this paper, we study the possibility of transforming a deep neural network to another network with a different number of units or layers, which can be…

Machine Learning · Computer Science 2019-05-29 Abhinav Kumar , Thiago Serra , Srikumar Ramalingam

We prove an impossibility result, which in the context of function learning says the following: under certain conditions, it is impossible to simultaneously learn symmetries and functions equivariant under them using an ansatz consisting of…

Machine Learning · Statistics 2022-10-19 Vasco Portilheiro

Permutation equivariant neural networks are often constructed using tensor powers of $\mathbb{R}^{n}$ as their layer spaces. We show that all of the weight matrices that appear in these neural networks can be obtained from Schur-Weyl…

Machine Learning · Computer Science 2024-08-09 Edward Pearce-Crump

Neural networks are known to be a class of highly expressive functions able to fit even random input-output mappings with $100\%$ accuracy. In this work, we present properties of neural networks that complement this aspect of expressivity.…

We develop a uniform theoretical approach towards the analysis of various neural network connectivity architectures by introducing the notion of a quiver neural network. Inspired by quiver representation theory in mathematics, this approach…

Machine Learning · Computer Science 2022-07-27 Iordan Ganev , Robin Walters

Deep neural networks, particularly those employing Rectified Linear Units (ReLU), are often perceived as complex, high-dimensional, non-linear systems. This complexity poses a significant challenge to understanding their internal learning…

Machine Learning · Computer Science 2025-11-11 Longqing Ye

ReLU neural networks define piecewise linear functions of their inputs. However, initializing and training a neural network is very different from fitting a linear spline. In this paper, we expand empirically upon previous theoretical work…

Machine Learning · Statistics 2016-11-30 Kevin K. Chen , Anthony Gamst , Alden Walker

We point out that (continuous or discontinuous) piecewise linear functions on a convex polytope mesh can be represented by two-hidden-layer ReLU neural networks in a weak sense. In addition, the numbers of neurons of the two hidden layers…

Numerical Analysis · Mathematics 2026-01-06 Pengzhan Jin

Many scientific problems require to process data in the form of geometric graphs. Unlike generic graph data, geometric graphs exhibit symmetries of translations, rotations, and/or reflections. Researchers have leveraged such inductive bias…

Machine Learning · Computer Science 2022-02-23 Jiaqi Han , Yu Rong , Tingyang Xu , Wenbing Huang

The universal approximation theorem establishes that neural networks can approximate any continuous function on a compact set. Later works in approximation theory provide quantitative approximation rates for ReLU networks on the class of…

Machine Learning · Computer Science 2026-04-17 Jonathan W. Siegel , Snir Hordan , Hannah Lawrence , Ali Syed , Nadav Dym

Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or equivariant (permutation of the input permutes the output). In this paper,…

Machine Learning · Computer Science 2019-10-25 Nicolas Keriven , Gabriel Peyré

We define and establish the conditions for `equivalent neural networks' - neural networks with different weights, biases, and threshold functions that result in the same associated function. We prove that given a neural network…

Machine Learning · Computer Science 2021-09-09 Dinesh Valluri , Rory Campbell

Permutation equivariant neural networks are typically used to learn from data that lives on a graph. However, for any graph $G$ that has $n$ vertices, using the symmetric group $S_n$ as its group of symmetries does not take into account the…

Machine Learning · Computer Science 2024-05-29 Edward Pearce-Crump , William J. Knottenbelt

Equivariant networks have been adopted in many 3-D learning areas. Here we identify a fundamental limitation of these networks: their ambiguity to symmetries. Equivariant networks cannot complete symmetry-dependent tasks like segmenting a…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Sidhika Balachandar , Adrien Poulenard , Congyue Deng , Leonidas Guibas

The training process of neural networks usually optimize weights and bias parameters of linear transformations, while nonlinear activation functions are pre-specified and fixed. This work develops a systematic approach to constructing…

Machine Learning · Computer Science 2024-10-29 Zhengqi Liu , Shuhao Cao , Yuwen Li , Ludmil Zikatanov

The principle of translation equivariance (if an input image is translated an output image should be translated by the same amount), led to the development of convolutional neural networks that revolutionized machine vision. Other…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Zachary Schlamowitz , Andrew Bennecke , Daniel J. Tward

Steerable convolutional neural networks (CNNs) provide a general framework for building neural networks equivariant to translations and transformations of an origin-preserving group $G$, such as reflections and rotations. They rely on…

Machine Learning · Computer Science 2023-10-30 Maksim Zhdanov , Nico Hoffmann , Gabriele Cesa

Convolutional neural networks owe much of their success to hard-coding translation equivariance. Quantum convolutional neural networks (QCNNs) have been proposed as near-term quantum analogues, but the relevant notion of translation depends…

Quantum Physics · Physics 2026-04-28 Dmitry Chirkov , Igor Lobanov

Previous work on symmetric group equivariant neural networks generally only considered the case where the group acts by permuting the elements of a single vector. In this paper we derive formulae for general permutation equivariant layers,…

Machine Learning · Computer Science 2020-04-09 Erik Henning Thiede , Truong Son Hy , Risi Kondor
‹ Prev 1 4 5 6 7 8 10 Next ›