paper-with-me

Papers

A Primer for the Walsh Transform

2023-11-03 · Devin Greene

A mathematical development of the Walsh transform, Walsh basis, and Walsh coefficients is given. The author was prompted to write this by a wish to give a unified treatment of epistatic coordinates as they are used in evolutionary biology. At the end of the article, opinions are expressed regarding the usefulness of these concepts for the practical researcher.

📄 PDF Abstract BibTeX arXiv:2311.02177

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multiallelic Walsh transforms

2023-11-28 · Devin Greene

A closed formula multiallelic Walsh (or Hadamard) transform is introduced. Basic results are derived, and a statistical interpretation of some of the resulting linear forms is discussed.

Primer: Searching for Efficient Transformers for Language Modeling

2021-09-17 · David R. So, Wojciech Mańke, Hanxiao Liu, Zihang Dai 외

Large Transformer models have been central to recent advances in natural language processing. The training and inference costs of these models, however, have grown rapidly and become prohibitively expensive. Here we aim …

Language ModelingLanguage Modelling

Searching for Efficient Transformers for Language Modeling

2021-12-01 · NeurIPS 2021 12 · David So, Wojciech Mańke, Hanxiao Liu, Zihang Dai 외

Large Transformer models have been central to recent advances in natural language processing. The training and inference costs of these models, however, have grown rapidly and become prohibitively expensive. Here we aim …

Language ModelingLanguage Modelling

Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks

2021-04-14 · Hongyi Pan, Diaa Dabawi, Ahmet Enis Cetin

In this paper, we propose a novel layer based on fast Walsh-Hadamard transform (WHT) and smooth-thresholding to replace $1\times 1$ convolution layers in deep neural networks. In the WHT domain, we denoise the transform …

Walsh-Hadamard Neural Operators for Solving PDEs with Discontinuous Coefficients

2025-11-10 · Giorgio M. Cavallazzi, Miguel Pérez Cuadrado, Alfredo Pinelli arxiv

Neural operators have emerged as powerful tools for learning solution operators of partial differential equations (PDEs). However, standard spectral methods based on Fourier transforms struggle with problems involving di…