English
Related papers

Related papers: Geometry of Polynomial Neural Networks

200 papers

We study convolutional neural networks with monomial activation functions. Specifically, we prove that their parameterization map is regular and is an isomorphism almost everywhere, up to rescaling the filters. By leveraging on tools from…

Machine Learning · Computer Science 2025-03-04 Vahid Shahverdi , Giovanni Luca Marchetti , Kathlén Kohn

We study deep neural networks with polynomial activations, particularly their expressive power. For a fixed architecture and activation degree, a polynomial neural network defines an algebraic map from weights to polynomials. The image of…

Machine Learning · Computer Science 2019-05-30 Joe Kileel , Matthew Trager , Joan Bruna

In this paper, we study linear convolutional networks with one-dimensional filters and arbitrary strides. The neuromanifold of such a network is a semialgebraic set, represented by a space of polynomials admitting specific factorizations.…

Algebraic Geometry · Mathematics 2024-01-31 Vahid Shahverdi

We study the expressivity of rational neural networks (RationalNets) through the lens of algebraic geometry. We consider rational functions that arise from a given RationalNet to be tuples of fractions of homogeneous polynomials of fixed…

Algebraic Geometry · Mathematics 2025-09-16 Alexandros Grosdos , Elina Robeva , Maksym Zubkov

We study function spaces parametrized by neural networks, referred to as neuromanifolds. Specifically, we focus on deep Multi-Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs) with an activation function that is a…

Machine Learning · Computer Science 2026-02-16 Vahid Shahverdi , Giovanni Luca Marchetti , Kathlén Kohn

In this position paper, we promote the study of function spaces parameterized by machine learning models through the lens of algebraic geometry. To this end, we focus on algebraic models, such as neural networks with polynomial activations,…

Machine Learning · Computer Science 2025-06-03 Giovanni Luca Marchetti , Vahid Shahverdi , Stefano Mereta , Matthew Trager , Kathlén Kohn

Deep learning models are often considered black boxes due to their complex hierarchical transformations. Identifying suitable architectures is crucial for maximizing predictive performance with limited data. Understanding the geometric…

Machine Learning · Computer Science 2025-03-11 Michael Wienczkowski , Addisu Desta , Paschal Ugochukwu

We study the expressive power of deep polynomial neural networks through the geometry of their neurovariety. We introduce the notion of the activation degree threshold of a network architecture to express when the dimension of the…

Machine Learning · Computer Science 2025-10-01 Bella Finkel , Jose Israel Rodriguez , Chenxi Wu , Thomas Yahl

Polynomial Neural Networks (PNNs) possess a rich algebraic and geometric structure. However, their identifiability -- a key property for ensuring interpretability -- remains poorly understood. In this work, we present a comprehensive…

Machine Learning · Computer Science 2026-02-03 Konstantin Usevich , Ricardo Borsoi , Clara Dérand , Marianne Clausel

The empirical results suggest that the learnability of a neural network is directly related to its size. To mathematically prove this, we borrow a tool in topological algebra: Betti numbers to measure the topological geometric complexity of…

Machine Learning · Computer Science 2021-11-05 Ji Yang , Lu Sang , Daniel Cremers

Despite significant advances in the field of deep learning in applications to various fields, explaining the inner processes of deep learning models remains an important and open question. The purpose of this article is to describe and…

Machine Learning · Computer Science 2022-04-20 German Magai , Anton Ayzenberg

Why do deep neural networks (DNNs) benefit from very high dimensional parameter spaces? Their huge parameter complexities vs stunning performance in practice is all the more intriguing and not explainable using the standard theory of model…

Machine Learning · Computer Science 2025-06-12 Ke Sun , Frank Nielsen

Deep neural networks can approximate functions on different types of data, from images to graphs, with varied underlying structure. This underlying structure can be viewed as the geometry of the data manifold. By extending recent advances…

Machine Learning · Computer Science 2023-01-03 Saket Tiwari , George Konidaris

We study robustness verification of neural networks via metric algebraic geometry. For polynomial neural networks, certifying a robustness radius amounts to computing the distance to the algebraic decision boundary. We use the Euclidean…

Machine Learning · Statistics 2026-04-20 Yulia Alexandr , Hao Duan , Guido Montúfar

Artificial neural networks (ANNs) are powerful tools capable of approximating any arbitrary mathematical function, but their interpretability remains limited, rendering them as black box models. To address this issue, numerous methods have…

Machine Learning · Computer Science 2024-06-11 Abhiram Anand Thiruthummal , Eun-jin Kim , Sergiy Shelyag

Many tasks require mapping continuous input data (e.g. images) to discrete task outputs (e.g. class labels). Yet, how neural networks learn to perform such discrete computations on continuous data manifolds remains poorly understood. Here,…

Machine Learning · Computer Science 2025-12-02 Julian Brandon , Angus Chadwick , Arthur Pellegrino

We propose an algebraic geometric framework to study the expressivity of linear activation neural networks. A particular quantity of neural networks that has been actively studied is the number of linear regions, which gives a…

Machine Learning · Computer Science 2024-10-10 Paul Lezeau , Thomas Walker , Yueqi Cao , Shiv Bhatia , Anthea Monod

Recently, deep learning approaches have been extensively investigated to reconstruct images from accelerated magnetic resonance image (MRI) acquisition. Although these approaches provide significant performance gain compared to compressed…

Computer Vision and Pattern Recognition · Computer Science 2020-10-28 Eunju Cha , Gyutaek Oh , Jong Chul Ye

We study polynomial group convolutional neural networks (PGCNNs) for an arbitrary finite group $G$. In particular, we introduce a new mathematical framework for PGCNNs using the language of graded group algebras. This framework yields two…

Machine Learning · Computer Science 2026-04-01 Yacoub Hendi , Daniel Persson , Magdalena Larfors

This study explores the number of neurons required for a Rectified Linear Unit (ReLU) neural network to approximate multivariate monomials. We establish an exponential lower bound on the complexity of any shallow network approximating the…

Machine Learning · Computer Science 2023-05-17 Itai Shapira
‹ Prev 1 2 3 10 Next ›