查询词典 neural network

In this paper, we propose a learning algorithm of the Hopfield neural network which can escape from local minimum.

在本论文中，我们提出了两种基于离散Hopfield神经元网络的跳出局部极小点的启发式算法。

Usually, in traditional BP neural network model, data fitting may become trapped at a local minimum.

在本文中提出了一种针对新型双权值神经元网络的数据拟合算法。

The paper introduces a method to identify the log curve shape using self-organization neural network.

这里介绍一种利用自组织神经网络识别曲线形态的方法。

The sonic log curve is reconstructed by using BP neural network technology combining SP,Rt,Gr curves data as to enhance the information quality of curve reconstruction and ensure the accuracy of curve reconstruction.

运用BP神经网络技术综合了自然电位、电阻率、自然伽马等多条曲线的信息对声波曲线进行重构，以此增加曲线重构的信息量，为曲线重构的准确性提供了保障。

Based on the precessors′achievements, this thesis did a daring and beneficial exploration from geological model and log response of ordinary log curve, that is new research thought in the view of wavelet tranform skill, rock volume physical mathemal model and ordinary log neural network nonlinear inverse filter skill to improve log curve resolution in thin beds.

本文在借鉴前人研究成果的基础上，作了大胆有益的探索，针对裂缝性碳酸盐岩剖面的地质模型和测井响应特点，提出并建立了一套改善常规测井曲线纵向分辨率的新方法。

A knowledge representation method called Logical Neural Network Element Rule of integrating rule-based semantic structure with numeric-based counectionist architecture with learning capability is proposed.

具体提出了一种将基于规则、具有语义的结构与基于数字、具有学习能力的连接机制集成为一体的、被作者称为逻辑神经网络原子的知识表示方法。

This paper describes in brief the lithologic profiles and the geophysical logging curves of the low resistivity oil and gas layers in Tabei area, analyzes the origin of the low resistivity oil and gas reservoirs in that area, and deals emphatically with the principle of applying the neural network to recognizing oil and gas layers, oil-water layers, water layers and dry layers.

简要介绍了塔北低阻油气层岩性剖面、低阻油气层地球物理测井曲线特征，分析了塔北地区低阻油气储层成因，重点论述BP人工神经网络识别油气层、油水同层、水层和干层的方法原理。

BP neural network algorithm, has an established low-rise, according to gradient descent learning rules.

详细说明：神经网络BP算法，具有可设的层数，按梯度下降的学习规则。

An artificial neural network approach for predicting macroeconomics is presented in this paper.

人工神经网络应用于宏观经济预测具有广泛的实际应用前景。

Artificial neural network is an effective non-traditional modeling tool with a strong self-learning ability. It's good at not only thinking, summarizing, analogizing, reasoning, but also analyzing and extracting the law of macrostatistics from a large number of statistical data. At the same time, it also has a strong robustness, fault tolerance as well as formidable parallel computing ability.

人工神经网络具有很强的自学习能力，善于联想、概括、类比和推理，能从大量统计资料中分析提取宏观统计规律，同时具有很强的鲁棒性、容错性以及强大并行计算能力，是进行非传统建模的有效工具。

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。