首页>
外国专利>
NEURAL NETWORK TRAINING DATA SELECTION USING MEMORY REDUCED CLUSTER ANALYSIS FOR FIELD MODEL DEVELOPMENT
NEURAL NETWORK TRAINING DATA SELECTION USING MEMORY REDUCED CLUSTER ANALYSIS FOR FIELD MODEL DEVELOPMENT
展开▼
机译:基于内存减少聚类分析的神经网络训练数据选择模型研究
展开▼
页面导航
摘要
著录项
相似文献
摘要
A system and method for selecting a training data set from a set ofmultidimensional geophysical input data samples for training a model topredict target data. The input data may be data sets produced by a pulsedneutron logging tool at multiple depth points in a cases well. Target data maybe responses of an open hole logging tool. The input data is divided intoclusters (16, 24). Actual target data from the training well is linked to theclusters. The linked clusters are analyzed for variance, etc. and fuzzyinference (34) is used to select a portion of each cluster (36) to include ina training set. The reduced set is used to train a model, such as anartificial neural network. The trained model may then be used to producesynthetic open hole logs in response to inputs of cased hole log data.
展开▼