English
Related papers

Related papers: NegaBent, No Regrets: Evolving Spectrally Flat Boo…

200 papers

We introduce Boolformer, a Transformer-based model trained to perform end-to-end symbolic regression of Boolean functions. First, we show that it can predict compact formulas for complex functions not seen during training, given their full…

Machine Learning · Computer Science 2025-07-18 Stéphane d'Ascoli , Arthur Renard , Vassilis Papadopoulos , Samy Bengio , Josh Susskind , Emmanuel Abbé

Nonparametric extension of tensor regression is proposed. Nonlinearity in a high-dimensional tensor space is broken into simple local functions by incorporating low-rank tensor decomposition. Compared to naive nonparametric approaches, our…

Machine Learning · Statistics 2016-03-09 Masaaki Imaizumi , Kohei Hayashi

Set function learning has emerged as a crucial area in machine learning, addressing the challenge of modeling functions that take sets as inputs. Unlike traditional machine learning that involves fixed-size input vectors where the order of…

Machine Learning · Computer Science 2025-01-28 Jiahao Xie , Guangmo Tong

Recently it has been proven that simple GP systems can efficiently evolve a conjunction of $n$ variables if they are equipped with the minimal required components. In this paper, we make a considerable step forward by analysing the…

Neural and Evolutionary Computing · Computer Science 2023-10-09 Benjamin Doerr , Andrei Lissovoi , Pietro S. Oliveto

We propose the introduction of nonlinear operation into the feature generation process in convolutional neural networks. This nonlinearity can be implemented in various ways. First we discuss the use of nonlinearities in the process of data…

Machine Learning · Computer Science 2019-05-30 Gavneet Singh Chadha , Andreas Schwung

Bent functions, which are maximally nonlinear Boolean functions with even numbers of variables and whose Hamming distance to the set of all affine functions equals $2^{n-1}\pm 2^{\frac{n}{2}-1}$, were introduced by Rothaus in 1976 when he…

Information Theory · Computer Science 2012-05-08 Chunming Tang , Yanfeng Qi , Maozhi Xu , Baocheng Wang , Yixian Yang

Background: Windowed Fourier decompositions (WFD) are widely used in measuring stationary and non-stationary spectral phenomena and in describing pairwise relationships among multiple signals. Although a variety of WFDs see frequent…

Quantitative Methods · Quantitative Biology 2019-01-30 Christopher K. Kovach , Phillip E. Gander

Traditional approaches to estimating beta in finance often involve rigid assumptions and fail to adequately capture beta dynamics, limiting their effectiveness in use cases like hedging. To address these limitations, we have developed a…

Statistical Finance · Quantitative Finance 2024-10-29 Yuxin Liu , Jimin Lin , Achintya Gopal

We provide a mathematical interpretation of convolutional (or message passing) neural networks by using presheaves and copresheaves of the set of continuous functions over a topological space. Based on this interpretation, we formulate a…

Machine Learning · Computer Science 2026-04-28 Sun Woo Park , Yun Young Choi , U Jin Choi , Youngho Woo

Random boolean networks are a model of genetic regulatory networks that has proven able to describe experimental data in biology. They not only reproduce important phenomena in cell dynamics, but they are also extremely interesting from a…

Dynamical Systems · Mathematics 2015-02-26 Marco Villani , Davide Campioli , Chiara Damiani , Andrea Roli , Alessandro Filisetti , Roberto Serra

Gleason's theorem asserts the equivalence of von Neumann's density operator formalism of quantum mechanics and frame functions, which are functions on the pure states that sum to 1 on any orthonormal basis of Hilbert space of dimension at…

Quantum Physics · Physics 2018-08-16 Jiri Lebl , Asif Shakeel , Nolan Wallach

Majority of Artificial Neural Network (ANN) implementations in autonomous systems use a fixed/user-prescribed network topology, leading to sub-optimal performance and low portability. The existing neuro-evolution of augmenting topology or…

Neural and Evolutionary Computing · Computer Science 2018-07-24 Sharat Chidambaran , Amir Behjat , Souma Chowdhury

Bent functions can be classified into regular bent functions, weakly regular but not regular bent functions, and non-weakly regular bent functions. Regular and weakly regular bent functions always appear in pairs since their duals are also…

Information Theory · Computer Science 2015-11-10 Ayca Cesmelioglu , Wilfried Meidl , Alexander Pott

Convolutional Neural Networks (CNNs) are a class of artificial neural networks whose computational blocks use convolution, together with other linear and non-linear operations, to perform classification or regression. This paper explores…

Computer Vision and Pattern Recognition · Computer Science 2018-10-09 Victor Stamatescu , Mark D. McDonnell

Systems hosting flat bands offer a powerful platform for exploring strong correlation physics. Theoretically topological degeneracy rising in systems with non-trivial topological orders on periodic manifolds of non-zero genus can generate…

Superconductivity · Physics 2026-01-07 Yuge Chen , Hui Yu , Yun-Peng Huang , Zhen-Yu Zheng , Jiangping Hu

This paper proposes a low order geometrically exact flexible beam formulation based on the utilisation of generic beam shape functions to approximate distributed kinematic properties of the deformed structure. The proposed nonlinear beam…

Classical Physics · Physics 2018-09-05 C. Howcroft , R. G. Cook , S. A. Neild , M. H. Lowenberg , J. E. Cooper , E. B. Coetzee

We show examples of total Boolean functions that depend on $n$ variables and have spectral sensitivity $\Theta(\sqrt{\log n})$, which is asymptotically minimal. Our main new function combines the Hamming code with the Boolean address…

Computational Complexity · Computer Science 2025-02-21 Krišjānis Prūsis , Jevgēnijs Vihrovs

We study the most-informative Boolean function conjecture using a differential equation approach. This leads to a formulation of a functional inequality on finite-dimensional random variables. We also develop a similar inequality in the…

Information Theory · Computer Science 2025-02-17 Zijie Chen , Amin Gohari , Chandra Nair

An important problem in machine learning theory is to understand the approximation and generalization properties of two-layer neural networks in high dimensions. To this end, researchers have introduced the Barron space…

Machine Learning · Statistics 2024-01-02 Lei Wu

Most existing deep learning-based pan-sharpening methods have several widely recognized issues, such as spectral distortion and insufficient spatial texture enhancement, we propose a novel pan-sharpening convolutional neural network based…

Computer Vision and Pattern Recognition · Computer Science 2021-05-26 Jiaming Wang , Zhenfeng Shao , Xiao Huang , Tao Lu , Ruiqian Zhang , Jiayi Ma