Using Algebra of Hyper-Dimensional Vectors for Heuristic Representation of Data While Training Wide Neural Networks

机译：在训练宽泛神经网络的同时使用超维向量的代数进行数据的启发式表示

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

The method of heuristic data representation in broad artificial neural networks training using the algebra of binary vectors of large length (hyper-size vectors) is offered in the article. The idea of data decentralization in a binary vector is the basis for a data hyper-size representation. The usage of a traditional data structure presupposes that a binary vector can be divided into two parts where each of them stores some specific value of a data structure field. Such vector division is impossible in a decentralized representation. Each bit of a hyper-size vector stores to some extent structure fields all at once and at the same time all bits of a hyper-size vector are necessary for getting a specific value of a field. Such a representation of data is similar to a traditional one for brain natural neural networks. According to the authors' view point its application will allow to improve the recognition quality and in the future it can lead to the creation of crucially new methodology of machine training and artificial intelligence.

机译：本文提供了使用大长度的二进制向量（超大向量）的代数在广泛的人工神经网络训练中启发式数据表示的方法。二进制向量中数据分散的想法是数据超大尺寸表示的基础。使用传统数据结构的前提是，二进制矢量可以分为两部分，每个部分都存储数据结构字段的某些特定值。在分散的表示中，这种矢量划分是不可能的。超大尺寸向量的每一位都在某种程度上一次存储了结构域，同时，超大尺寸向量的所有位对于获取字段的特定值都是必需的。数据的这种表示类似于脑自然神经网络的传统表示。根据作者的观点，它的应用将有助于提高识别质量，并且在将来它可以导致创建至关重要的机器培训和人工智能新方法。

著录项

来源
《International Conference Complex Systems: Control and Modeling Problems》|2019年|168-171|共4页
会议地点 Samara(RU)
作者
Dmitry Pashchenko; Dmitry Trokoz; Alexey Martyshkin; Mihail Sinev;
展开▼
作者单位

Penza State Technological University Penza Russia;

Penza State University Penza Russia;

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
artificial intelligence; data structures; learning (artificial intelligence); neural nets; vectors;

机译：人工智能;数据结构;学习（人工智能）；神经网络向量;

相似文献

外文文献
中文文献
专利

1. Training Neural Networks as Learning Data-Adaptive Kernels: Provable Representation and Approximation Benefits [J] . Dou Xialiang, Liang Tengyuan Journal of the American statistical association . 2021,第535期

机译：培训神经网络作为学习数据 - 自适应核：可提供的表示和近似效益
2. Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN) [J] . Biswajeet Pradhan, Seyed Amir Naghibi, Bahareh Kalantar, Geomatics,Natural Hazards & Risk . 2018,第1期

机译：评估训练数据选择对滑坡敏感性图的影响：支持向量机（SVM），逻辑回归（LR）和人工神经网络（ANN）之间的比较
3. Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN) [J] . Biswajeet Pradhan, Seyed Amir Naghibi, Bahareh Kalantar, Geomatics,Natural Hazards & Risk . 2018,第1期

机译：评估训练数据选择对滑坡敏感性图的影响：支持向量机（SVM），逻辑回归（LR）和人工神经网络（ANN）之间的比较
4. Using Algebra of Hyper-Dimensional Vectors for Heuristic Representation of Data While Training Wide Neural Networks [C] . Dmitry Pashchenko, Dmitry Trokoz, Alexey Martyshkin, International Conference Complex Systems: Control and Modeling Problems . 2019

机译：在培训广播神经网络时，使用超尺寸向量的超尺寸向量的成像表示数据
5. Synthesizing additional training data to increase the classification accuracy of visual data using feed-forward neural networks on small datasets. [D] . Qumsieh, Rafi. 2017

机译：在小型数据集上使用前馈神经网络合成其他训练数据，以提高视觉数据的分类准确性。
6. Vector algebra in the analysis of genome-wide expression data [O] . Finny G Kuruvilla, Peter J Park, Stuart L Schreiber 2002

机译：向量代数在全基因组表达数据分析中的应用
7. Figure 1: Workflow diagram for toxify, including preprocessing of training data, filtering by size and zero padding, converting numeric vectors as Atchley factors, and training on neural network using gated recurrent units. [O] . -1

机译：图1：oxify的工作流程图，包括培训数据的预处理，尺寸过滤和零填充，将数字向量转换为atchley因子，以及使用门控复发单元对神经网络进行培训。
8. Construction Heuristics for Geometry and a Vector Algebra Representation of Geometry [R] . Wong, R. 1972

机译：几何的构造启发式和几何的向量代数表示

Using Algebra of Hyper-Dimensional Vectors for Heuristic Representation of Data While Training Wide Neural Networks

摘要

著录项

相似文献

相关主题

期刊订阅