搜索资源列表
TransferLearning
- 迁移学习智能信息处理的一种有效方法 上传的为英文资料-Migration Study
transfer-learning
- 迁移学习的经典文章,大多为国际顶级会议论文-Transfer of learning classic articles, most of the international top-level Conference Papers
TLLinks
- 会议讲义迁移学习内容,是迁移学习香港大学的大牛杨老师的讲义-transfer learning link
transfer--learning
- 迁移学习 论文 基于迁移学习的跨领域排序学习算法研究-Migration study of cross-cutting paper-based transfer learning learning algorithm for sorting
C_TraDaBoost
- 迁移学习目前是机器学习的热门领域,基于戴文渊的“Boosting for Transfer Learning”,很有学习价值,这里是TraDaBoost算法的源代码。-For transfer learning packets: 20_newsgroups, facilitate the use of learning
61-papers-about-transfer-leanring
- 61篇迁移学习方面的经典文献,其中英文60篇,中文文献1篇-61 classical papers about transfer leanring
C_TraDaBoost
- 迁移学习代码,大家可以看看,对NLP有用。-Transfer learning code
kdd09transfer.tar
- 迁移学习程序,适用于NLP问题,大家可以看看。-To migrate learning program suitable for NLP problems
mtl_feat
- 一中多任务迁移学习算法,非常实用,而且容易理解,上传给大家,资源共享-transfer learning tools
codeadata_TriTL
- 三重迁移学习代码和数据,用于发现文本分类中共享和独特的概念。-Triple learning code and data migration. Exploiting both Shared and Distinct Concepts for Text Classification
htl4ic
- 使用新兴的机器学习方法:迁移学习进行图片分类,分类效果明显提高。-Use the emerging machine learning methods: migration study carried pictures segments, segment results improved significantly.
sick
- 迁移学习 领域适应性 机器学习 学习代码(Transfer learning Domain Adaptation Machine Learning Coding study Inductive Learning Transductive Learning)
pytorch-adda-master
- 迁移学习框架ADDA, python 代码,整体可运行(a fr a mework of transfer learning)
C_TraDaBoost
- 戴文渊---Boosting for Transfer Learning,TraDaBoost算法的源代码。(Dai Wenyuan ---Boosting for Transfer Learning, the source code of the TraDaBoost algorithm.)
cell
- 2018年2月cell封面论文代码,压缩包中有对这篇文章的解读,ppt文件(Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning)
剪枝操作.tar
- 这是用于人脸识别相关论文,包括迁移学习,神经网络训练学习率,超参数设置等(This is for face recognition related papers, including migration learning, neural network training learning rate, super parameter setting, etc.)
fast_self taught learning
- transfer learning---self taught learning
sparse-cvpr13
- 使用迁移学习和稀疏编码来实现不同领域之间的适配,是一种基于特征表示的迁移学习(This method is designed for image clustering and classification and called sparse subspace clustering.)
利用残差网络进行图像融合
- 利用深度学习的方法进行红外图像和可见光图像的融合,该方法受启发于最近比较流行的迁移学习,利用可见光的数据集训练网络,从而提取出红外和可见光图像的特征,最后进行图像的融合。
domain_adaptation-master
- 迁移学习领域自适应实现跨领域分类,扩充样本数据库(Adaptive implementation of cross-domain classification in transfer learning domain and expansion of sample database)