迁移学习专注于解决监督学习在小数据集上难以获得好的分类效果的问题,与传统监督学习的基本假设相比,它并不要求训练集和测试集服从相同或相似的数据分布。通过在标注资源丰富的源语言中学习,并将目标语言的文档投影到与源语言相同的...迁移学习专注于解决监督学习在小数据集上难以获得好的分类效果的问题,与传统监督学习的基本假设相比,它并不要求训练集和测试集服从相同或相似的数据分布。通过在标注资源丰富的源语言中学习,并将目标语言的文档投影到与源语言相同的特征空间中去,从而解决目标语言因数据量较小而难以获得好的分类模型的问题。选择亚马逊在书籍、DVD和音乐类目下的中文、英文和日文评论作为实验数据,情感分析作为研究任务,提出了一种新的跨语言深度表示学习模型(cross lingual deep representation learning,CLDRL),实现了不同语言环境下的知识迁移。实验结果表明,CLDRL模型在跨语言环境下最优F1值达到了78.59%,证明了该模型的有效性。展开更多
Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extrac...Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extraction and model construction.Firstly,the convolutional neural network(CNN)features of the face are extracted by the trained deep learning network.Next,the steady-state and dynamic classifiers for face recognition are constructed based on the CNN features and Haar features respectively,with two-stage sparse representation introduced in the process of constructing the steady-state classifier and the feature templates with high reliability are dynamically selected as alternative templates from the sparse representation template dictionary constructed using the CNN features.Finally,the results of face recognition are given based on the classification results of the steady-state classifier and the dynamic classifier together.Based on this,the feature weights of the steady-state classifier template are adjusted in real time and the dictionary set is dynamically updated to reduce the probability of irrelevant features entering the dictionary set.The average recognition accuracy of this method is 94.45%on the CMU PIE face database and 96.58%on the AR face database,which is significantly improved compared with that of the traditional face recognition methods.展开更多
文摘迁移学习专注于解决监督学习在小数据集上难以获得好的分类效果的问题,与传统监督学习的基本假设相比,它并不要求训练集和测试集服从相同或相似的数据分布。通过在标注资源丰富的源语言中学习,并将目标语言的文档投影到与源语言相同的特征空间中去,从而解决目标语言因数据量较小而难以获得好的分类模型的问题。选择亚马逊在书籍、DVD和音乐类目下的中文、英文和日文评论作为实验数据,情感分析作为研究任务,提出了一种新的跨语言深度表示学习模型(cross lingual deep representation learning,CLDRL),实现了不同语言环境下的知识迁移。实验结果表明,CLDRL模型在跨语言环境下最优F1值达到了78.59%,证明了该模型的有效性。
基金the financial support from Natural Science Foundation of Gansu Province(Nos.22JR5RA217,22JR5RA216)Lanzhou Science and Technology Program(No.2022-2-111)+1 种基金Lanzhou University of Arts and Sciences School Innovation Fund Project(No.XJ2022000103)Lanzhou College of Arts and Sciences 2023 Talent Cultivation Quality Improvement Project(No.2023-ZL-jxzz-03)。
文摘Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extraction and model construction.Firstly,the convolutional neural network(CNN)features of the face are extracted by the trained deep learning network.Next,the steady-state and dynamic classifiers for face recognition are constructed based on the CNN features and Haar features respectively,with two-stage sparse representation introduced in the process of constructing the steady-state classifier and the feature templates with high reliability are dynamically selected as alternative templates from the sparse representation template dictionary constructed using the CNN features.Finally,the results of face recognition are given based on the classification results of the steady-state classifier and the dynamic classifier together.Based on this,the feature weights of the steady-state classifier template are adjusted in real time and the dictionary set is dynamically updated to reduce the probability of irrelevant features entering the dictionary set.The average recognition accuracy of this method is 94.45%on the CMU PIE face database and 96.58%on the AR face database,which is significantly improved compared with that of the traditional face recognition methods.
文摘因果推断可以帮助人们制定更加合理的决策方案,在电子商务和精准医学等领域有广泛的应用,其性能严重依赖对个体因果效应(Individual Treatment Effect,ITE)的准确估计,观察数据中存在的选择偏差与样本数量不一致问题都会影响ITE估计的准确性.对于选择偏差问题,现有的深度学习方法主要通过平衡所有协变量来进行缓解,但平衡协变量中与处理无关的噪声变量会导致对个体因果效应的估计不准确.对于样本数量不一致问题,这些方法主要通过在损失函数中添加样本权重来进行缓解,但其不能有效提升模型预测的准确性.提出一种基于深度表示学习的方法,通过g^(nn)和IPM(Integral Probability Metric)网络共同诱导神经网络得到协变量中非噪声变量的平衡共享表示,然后引入X-Net来缓解样本数量不一致问题.在半合成与真实数据集上的实验结果表明,提出的算法可以通过缓解样本选择偏差与样本数量不一致问题来提高模型ITE估计的准确性.
