arrow
返回

Deep Polynomial Neural Networks

delete2021-01-01
delete35
delete
OA
AI
G
Grigorios G. Chrysos *
S
Stylianos Moschoglou
G
Giorgos Bouritsas
J
Jiankang Deng
Y
Yannis Panagakis
S
Stefanos Zafeiriou
DOI:10.1109/TPAMI.2021.3058891delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
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 selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few). In this paper, we propose pi-Nets, a new class of function approximators based on polynomial expansions. pi-Nets are polynomial neural networks, i.e., the output is a high-order polynomial of the input. The unknown parameters, which are naturally represented by high-order tensors, are estimated through a collective tensor factorization with factors sharing. We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks. We empirically demonstrate that pi-Nets are very expressive and they even produce good results without the use of non-linear activation functions in a large battery of tasks and signals, i.e., images, graphs, and audio. When used in conjunction with activation functions, pi-Nets produce state-of-the-art results in three challenging tasks, i.e., image generation, face verification and 3D mesh representation learning. The source code is available at https://github.com/grigorisg9gr/polynomial_nets.
Keyword:
Polynomial neural networks
tensor decompositions
high-order polynomials
generative models
discriminative models
face verification
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Pattern Analysis and Machine Intelligence 封面图
IEEE Transactions on Pattern Analysis and Machine Intelligence
IF:
18.6
论文数:
1.1K
被引数:
9.8W

机构

E
Ecole Polytechnique Federale de Lausanne
学者数:
1.7W
论文数: 1.3W
被引数: 25
S
swiss federal institutes of technology domain
学者数:
9.0W
论文数: 8.0W
被引数: 163
I
Imperial College London
学者数:
8.3W
论文数: 7.3W
被引数: 11.1W
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
Requirement for Croquemort in Phagocytosis of Apoptotic Cells in Drosophila
err1999-06-18
err0
PREAI
errNathalie C. Franc; Pascal Heitzler; R. Alan B.; Ezekowitz; Kristin White
err分享
err收藏
err分享
err收藏
Synthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source以五氧化二磷为掺杂源合成n型半导体金刚石膜
err1990-10-01
err0
PREAI
errKen Okano; Hideo Kiyota; Tatsuya Iwasaki; Yoshitaka Nakamura; Yukio Akiba; Tateki Kurosu; Masamori Iida; Terutaro Nakamura
err分享
err收藏
学者 查看更多内容