English
Related papers

Related papers: Polynomial, trigonometric, and tropical activation…

200 papers

Researchers commonly believe that neural networks model a high-dimensional space but cannot give a clear definition of this space. What is this space? What is its dimension? And does it has finite dimensions? In this paper, we develop a…

Machine Learning · Computer Science 2023-05-10 John Chiang

An increasing number of computer vision tasks can be tackled with deep features, which are the intermediate outputs of a pre-trained Convolutional Neural Network. Despite the astonishing performance, deep features extracted from low-level…

Computer Vision and Pattern Recognition · Computer Science 2016-05-03 Lingxi Xie , Liang Zheng , Jingdong Wang , Alan Yuille , Qi Tian

Introduced is a methodology for adapting the topology of dense neural networks, enabled by isotropic activation functions. Achieved through prescribed reparameterisation symmetries and singular-value decomposition of affine maps, this…

Neural and Evolutionary Computing · Computer Science 2026-05-08 George Bird

Expressivity is one of the most significant issues in assessing neural networks. In this paper, we provide a quantitative analysis of the expressivity for the deep neural network (DNN) from its dynamic model, where the Hilbert space is…

Machine Learning · Computer Science 2019-12-24 Gege Zhang , Gangwei Li , Ningwei Shen , Weidong Zhang

Under mild conditions on the network initialization we derive a power series expansion for the Neural Tangent Kernel (NTK) of arbitrarily deep feedforward networks in the infinite width limit. We provide expressions for the coefficients of…

Machine Learning · Computer Science 2023-03-02 Michael Murray , Hui Jin , Benjamin Bowman , Guido Montufar

We consider deep neural networks, in which the output of each node is a quadratic function of its inputs. Similar to other deep architectures, these networks can compactly represent any function on a finite training set. The main goal of…

Machine Learning · Computer Science 2014-02-21 Roi Livni , Shai Shalev-Shwartz , Ohad Shamir

We present polynomial time and sample efficient algorithms for learning an unknown depth-2 feedforward neural network with general ReLU activations, under mild non-degeneracy assumptions. In particular, we consider learning an unknown…

Machine Learning · Computer Science 2021-08-03 Pranjal Awasthi , Alex Tang , Aravindan Vijayaraghavan

An algorithm is designed which decomposes a tropical univariate rational function into a composition of tropical binomials and trinomials. When a function is monotone, the composition consists just of binomials. Similar algorithms are…

Algebraic Geometry · Mathematics 2019-03-04 Dima Grigoriev

Currently, deep neural networks are the state of the art on problems such as speech recognition and computer vision. In this extended abstract, we show that shallow feed-forward networks can learn the complex functions previously learned by…

Machine Learning · Computer Science 2014-10-14 Lei Jimmy Ba , Rich Caruana

Neural networks have proven to be a highly effective tool for solving complex problems in many areas of life. Recently, their importance and practical usability have further been reinforced with the advent of deep learning. One of the…

Machine Learning · Computer Science 2024-02-15 Vladimír Kunc , Jiří Kléma

Multiplication of polynomials is among key operations in computer algebra which plays important roles in developing techniques for other commonly used polynomial operations such as division, evaluation/interpolation, and factorization. In…

Numerical Analysis · Mathematics 2022-06-02 S. Karami , M. Ahmadnasab , M. Hadizadeh , A. Amiraslani

We provide a theoretical study of a new family of orthogonal functions on the punctured complex plane solving the eigenvalue problems for some magnetic Laplacian perturbed by a singular vector potential with zero magnetic field modeling the…

Mathematical Physics · Physics 2022-11-29 Hajar Dkhissi , Allal Ghanmi

In this effort we propose a novel approach for reconstructing multivariate functions from training data, by identifying both a suitable network architecture and an initialization using polynomial-based approximations. Training deep neural…

Machine Learning · Computer Science 2019-05-29 Joseph Daws , Clayton G. Webster

This study explores novel activation functions that enhance the ability of neural networks to manipulate data topology during training. Building on the limitations of traditional activation functions like $\mathrm{ReLU}$, we propose…

Machine Learning · Computer Science 2025-07-18 Pavel Snopov , Oleg R. Musin

Deep Convolutional Neural Networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful…

Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e.g., citation networks or knowledge graphs. While several variants of GNNs…

Neural and Evolutionary Computing · Computer Science 2018-02-27 Simone Scardapane , Steven Van Vaerenbergh , Danilo Comminiello , Aurelio Uncini

We introduce and study filtrations of a matroid on a linearly ordered ground set, which are particular sequences of nested sets. A given basis can be decomposed into a uniquely defined sequence of bases of minors, such that these bases have…

Combinatorics · Mathematics 2018-07-19 Emeric Gioan , Michel Las Vergnas

Can algebraic geometry enhance the sharpness, robustness, and interpretability of modern neural reasoning models by equipping them with a mathematically grounded inductive bias? To answer this, we introduce Tropical Attention, an attention…

Machine Learning · Computer Science 2025-10-24 Baran Hashemi , Kurt Pasque , Chris Teska , Ruriko Yoshida

We present a framework for the construction of linearizations for scalar and matrix polynomials based on dual bases which, in the case of orthogonal polynomials, can be described by the associated recurrence relations. The framework…

Numerical Analysis · Mathematics 2016-07-06 Leonardo Robol , Raf Vandebril , Paul Van Dooren

We introduce a class of trainable nonlinear operators based on semirings that are suitable for use in neural networks. These operators generalize the traditional alternation of linear operators with activation functions in neural networks.…

Machine Learning · Computer Science 2025-03-11 Bart M. N. Smets , Peter D. Donker , Jim W. Portegies