查询词典 neural network

According to the inner product feature of sample space this paper takes the differential of fast changing parameters into input samples and puts forward a new neural network not to require to iterate learn, taking it for example recording data of the record system of a type of aeroengine and taking out identification to it.

根据样本空间的内积特性，在输入样本中引入快变参数的导数项，提出了一种无需迭代学习的内积神经网络。

A backpropagation neural network model with the input matrix composed of the characteristic indexes of pressure is proposed to classify the running state of refrigerating units in order to diagnose and forecast the leakage fault.

研究了冷库制冷机组制冷剂泄漏的特征，分析了泄漏引发的流量和压力参数变化情况，并提取了反映泄漏故障的特征指标，建立了能对制冷机组运行状态进行分类的神经网络模型，以诊断和预报泄漏故障的发生。

The main problem was in the representation of an input data for neural network.

主要的问题是在为神经网络输入数据的代表性。

A neural network was used to express the nonlinear function between input and output of the inverse kinematics of the robot.

利用神经网络逼近机器人逆运动学的输入与输出、利用改进的蚁群算法学习神经网络。

Power system ; Short-term load forecasting ; Fuzzy-rough sets ; Input variable selection ; Neural network ; Data mining

电力系统；短期负荷预测；模糊粗糙集；输入变量选择；神经网络；数据挖掘

The forecast data of grey prediction GM (1, 1) were used as the input variable of BP neural network, the actual output were as output variable.

将GM(1，1)预测模型的预测值作为BP神经网络的输入变量，实际值作为输出变量进行神经网络训练。

Discrimination for magnetizing inrush current of transformer based on artificial neural network was studied.

研究了基于神经网络方法的电力变压器励磁涌流鉴别。

This paper discusses the nonlinear inversion algorithms instructively andmainlystudytwokinds ofnonlinearinversionalgorithms: SimulatedAnnealingConjugate Grads and Artificial Neural Network Genetic Algorithms, these two methods can decrease the iteration times and avoiddroppinginto the local extremum, we do the model calculation and confirm thevalidityofthealgorithm.

对非线性反演算法进行了有益的探讨，主要研究了两种非线性混合优化反演算法：模拟退火共轭梯度混合反演和神经网络遗传反演算法，两种混合算法都达到了减少迭代次数、避免陷入局部极值的目的，并进行了模型试算，验证了算法的有效性。

And the accurate measurement result is of neural network whereas the intelligibility is of inductive learning.

该学习系统得到的结果是神经网络的判决精度并具有归纳学习的概念的可理解性。

In the first milestone, we'll build a simple GUI and the basic blocks to model neural network training and internetwork topologies.

在第一个阶段中，我们将建立一个简单的GUI和基本的块来为神经网络训练和内部联网拓扑建模。

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。