ID 原文 译文
47626 人工神经网络作为人工智能的分支，在模式识别、分类预测等方面已成功地解决了许多现代计算机难以解决的实际问题。然而随着人工智能的发展，神经网络的自主性特征学习功能越来越重要，人工神经网络虽然表现出了良好的智能特性， As the branch of artificial intelligence, artificial neural network solved many difficult practical problems inpattern recognition and classification prediction field successfully.
47627 但不能自主地学习特征。 However, they cannot learn the feature from networks.
47628 近年来，深度学习逐渐崛起，围绕深度神经网络的研究也越来越多，但其在地质储层参数预测领域的研究还很少。 In recent years, deep learning becomes more and more advanced, but the research on the field of geological reservoir pa-rameter prediction is still rare.
47629 提出了一种应用卷积神经网络对地质储层参数进行预测的方法，该方法不仅能对储层参数进行精确预测，而且可以得到储层特征集。 A method to predict reservoir parameters by convolutional neural network was presented, which can not only predict reservoir parameters accurately, but also get features of the geological reservoir.
47630 实验证明，卷积神经网络可以应用于地质储层参数预测，且预测精度较高， The study es-tablished the convolutional neural network model. Results show that the convolutional neural network can be used forreservoir parameter prediction, and get high prediction precision.
47631 同时卷积神经网络的卷积特征为储层地质建模与测井资料解释提供了重要的支持。 Moreover, convolutional features from convolutionalneural network provided important support for geological modeling and logging interpretation.
47632 提出一种面向多跳无线网络的多干扰源定位算法， A multiple jammer localization algorithm in multi-hop wireless networks was proposed.
47633 主要包括 3 个步骤：基于梯度下降法的分组投递率谷点推定、基于梯度上升法的接收干扰强度(RJSS, received jamming signal strength)峰点推定和聚类分析。 The proposed algo-rithm contained three steps, packet delivery ratio (PDR) valley point determination based on gradient descent algorithm,received jamming signal strength (RJSS) peak point determination based on gradient ascent algorithm and cluster analysis.
47634 首先，算法从多个初始节点出发，采用梯度下降法，沿着分组投递率梯度下降最快的方向逼近干扰源，直至到达分组投递率谷点； Firstly, the algorithm started from a few initial nodes and moved along the gradient descent direction of PDR to approachthe jammers until reaches the PDR valley point.
47635 然后应用功率自适应动态调整技术，采用梯度上升法，沿着接收干扰强度上升最快的方向继续逼近干扰源，直至接收干扰强度峰点（也称为 RJSS 停止节点）； Then, the algorithm moved toward the jammers using power adaptation technique based on RJSS gradient ascent process until it reached the RJSS peak point.