监督学习,supervised learning
1)supervised learning监督学习
1.Land evaluation based on agglomerative hierarchical cluster algorithm combining with supervised learning algorithm;融合监督学习与凝聚层次聚类的土地评价方法
2.Aimed at the problem of electroencephalography(EEG) pattern recognition in brain computer interfaces(BCIs),a classification method based on probabilistic neural network(PNN) with supervised learning was presented.针对脑机接口(BCI)研究中脑电信号(EEG)的模式识别问题,提出了一种基于有监督学习的概率神经网络(PNN)的分类方法。
3.The learning of connectionism,which consists mainly of supervised learning,intensive learning and unsupervised learning,is modelled after the learning of human beings.其学习是对人类学习的模拟,主要有监督学习、强化学习和无监督学习三种。
英文短句/例句

1.Comparison Between Supervised Learning and Unsupervised Learning in Neural Networks;神经网络内监督学习和无监督学习之比较
2.Research on Tongue Color Analysis Methods Based on Semi-Supervised Learning;基于半监督学习的舌色分析方法研究
3.Research on Neural Networks-based Semi-supervised Learning Methods基于神经网络的半监督学习方法研究
4.Semi-supervised Learning and Its Application to Intrusion Detection System半监督学习在入侵检测系统中的应用
5.Eyebrow image segmentation based on semi-supervised learning基于半监督学习的眉毛图像分割方法
6.Speaker Identification Algorithm of Semi-Supervised Learning Mechanism半监督学习机制下的说话人辨认算法
7.Study of Intrusion Detection Algorithm Based on Semi-supervised Learning基于半监督学习的入侵检测算法研究
8.The Research of Semi-Supervised Chinese Document Classification Algorithm;基于半监督学习的中文文档分类技术研究
9.An Unsupervised Approach to Term Variant Identification;一种基于无监督学习的词变体识别方法
10.Image Retrieval Combining Attention Model with Semi-supervised Learning结合显著性分析和半监督学习的图像检索算法
11.A Semi-Supervised Learning Algorithm Based on Lie Group and Application一种基于李群的半监督学习算法及应用研究
12.Research on Graph-based Semi-Supervised Learning Model and Classifier Design基于图的半监督学习模型研究与分类器设计
13.Studying Regulations and Improving Actual Results of Inner-Party Supervision;学习贯彻党内监督条例 切实提高党内监督实效
14.The useful countermeasures are: amplify surveillance mechanism; improve study and surveillance system; implement countermeasure.有效监督“一把手”的措施是:健全监督机制;加强学习;完善监督制度;落实监督措施。
15.Research on Surveillance and Evaluation of Web Courses’ Learning Effect;网络课程学习效果的监督与评价研究
16.The Study of the Manifold Learning Based Supervised Dimensionality Reduction Methods基于流形学习的有监督降维方法研究
17.α-based Supervised Orthogonal Projection Reduction by Affinity基于有监督流形学习的正交投影降维
18.Semi-supervised Text Categorization with Two Phases Co-training半监督的文本分类——两阶段协同学习
相关短句/例句

monitoring learning监督性学习
3)unsupervised learning非监督学习
1.Accelerating the Training of Feedforward Neural Networks Using Improving Unsupervised Learning Principle;用改进的非监督学习方法加速前馈神经网络的训练
2.Image object′s semantic hierarchy and its unsupervised learning algrithm图像目标语义层级结构及其非监督学习算法
3.Experiments show that these unsupervised learning methods had different characters in classifying land use/cover of remote sensing.结果表明三种非监督学习方法在进行遥感土地利用/覆盖分类过程中,在分类性能上有显著差异。
4)semi-supervised learning半监督学习
1.Making use of the unlabeled data in the semi-supervised learning;半监督学习中非标记数据的利用
2.Application based on semi-supervised learning algorithm to land evaluation;半监督学习算法在农用地分等中的应用
3.JPEG steganalysis based on Tri-training semi-supervised learning;基于Tri-training半监督学习的JPEG隐密分析方法
5)unsupervised learning无监督学习
1.Intelligent fire detection based on unsupervised learning clustering algorithm of Dignet基于Dignet无监督学习聚类算法的智能火灾探测
2.The learning of connectionism,which consists mainly of supervised learning,intensive learning and unsupervised learning,is modelled after the learning of human beings.其学习是对人类学习的模拟,主要有监督学习、强化学习和无监督学习三种。
3.The result of the feature selection in unsupervised learning is not as satisfactory as that in supervised learning.无监督学习环境下的特征选择往往无法取得像有监督学习环境下那样令人满意的效果。
6)supervised learning有监督学习
1.A Method of Choosing Web Services based on Supervised Learning Principle;一种基于有监督学习原理的Web服务选择方法
2.By using optimal cluster algorithm in combination with supervised learning of training system, functional approximation efficiency is improved.本文依据可加性模糊系统理论 ,提出了一种新的预测方法 ,利用聚类方法与有监督学习相结合的训练方法 ,提高了系统的函数逼近能力。
延伸阅读

监督学习  利用一组已知类别的样本调整分类器的参数,使其达到所要求性能的过程,也称为监督训练或有教师学习。正如人们通过已知病例学习诊断技术那样,计算机要通过学习才能具有识别各种事物和现象的能力。用来进行学习的材料就是与被识别对象属于同类的有限数量样本。监督学习中在给予计算机学习样本的同时,还告诉计算各个样本所属的类别。若所给的学习样本不带有类别信息,就是无监督学习。任何一种学习都有一定的目的,对于模式识别来说,就是要通过有限数量样本的学习,使分类器在对无限多个模式进行分类时所产生的错误概率最小。    不同设计方法的分类器有不同的学习算法。对于贝叶斯分类器来说,就是用学习样本估计特征向量的类条件概率密度函数。在已知类条件概率密度函数形式的条件下,用给定的独立和随机获取的样本集,根据最大似然法或贝叶斯学习估计出类条件概率密度函数的参数。例如,假定模式的特征向量服从正态分布,样本的平均特征向量和样本协方差矩阵就是正态分布的均值向量和协方差矩阵的最大似然估计。在类条件概率密度函数的形式未知的情况下,有各种非参数方法,用学习样本对类条件概率密度函数进行估计。在分类决策规则用判别函数表示的一般情况下,可以确定一个学习目标,例如使分类器对所给样本进行分类的结果尽可能与"教师"所给的类别一致,然后用迭代优化算法求取判别函数中的参数值。    在无监督学习的情况下,用全部学习样本可以估计混合概率密度函数,若认为每一模式类的概率密度函数只有一个极大值,则可以根据混合概率密度函数的形状求出用来把各类分开的分界面。