The invention relates to a method for generating matrix data of a convolutional neural network, and a learning system and a learning device using the convolutional neural network. In a method for generating matrix data of a convolutional neural network in which convolution operation is performed on the basis of matrix data in which vehicle information is arranged as matrix elements, the matrix data is composed of predetermined time series data in which each row continuously varies over time in the arrangement direction of each column, and the matrix data is stored in the array direction of each column. The time-series data is composed of first data having a high degree of influence on a convolution operation and second data having a lower degree of influence on the first data, and the convolution operation is performed using a kernel that divides the matrix data into a plurality of rows and a plurality of columns corresponding to predetermined coefficients. And arranging at least one row of the first data for each group of the plurality of rows corresponding to the coefficient.

    本公开涉及用于生成卷积神经网络的矩阵数据的方法以及使用卷积神经网络的学习系统和学习装置。在用于生成卷积神经网络的矩阵数据的方法中,该卷积神经网络基于矩阵数据进行卷积运算,车辆信息作为矩阵元素被排列在矩阵数据中,矩阵数据由预定的时间序列数据组成,其中各行在各列的排列方向上按时间连续变化,时间序列数据由对卷积运算的影响度高的第一数据和影响度低于第一数据的第二数据组成,使用内核进行卷积运算,该内核将矩阵数据划分为与预定的系数对应的多个行和多个列,并且针对与系数对应的多个行的每个组排列至少一行第一数据。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Method for generating matrix data of convolutional neural network, and learning system and learning apparatus using convolutional neural network


    Weitere Titelangaben:

    用于生成卷积神经网络的矩阵数据的方法、以及使用卷积神经网络的学习系统和学习装置


    Beteiligte:

    Erscheinungsdatum :

    2024-03-01


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G01D MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE , Anzeigen oder Aufzeichnen in Verbindung mit Messen allgemein / G01R Messen elektrischer Größen , MEASURING ELECTRIC VARIABLES / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung




    Human-Robot Interaction Using Reinforcement Learning and Convolutional Neural Network

    Khan, Yousuf / Otalvaro, Edier | BASE | 2020

    Freier Zugriff

    IMPROVED FACE RECOGNITION USING CONVOLUTIONAL NEURAL NETWORK WITH UNAIDED LEARNING

    Malathy, S / Vanitha, C.N. / Mohanasundari, M. et al. | IEEE | 2021


    Structural Damage Detection using Deep Convolutional Neural Network and Transfer Learning

    Feng, Chuncheng / Zhang, Hua / Wang, Shuang et al. | Springer Verlag | 2019


    Convolutional Neural Network for ASR

    Newatia, Sourav / Aggarwal, R.K. | IEEE | 2018