此Notebook旨在通过Python/Keras来验证 seq2seq神经网络如何做时间序列预测,尤其是在高维时间序列——也就是说,必须同步预测大量(10万+)序列的场景下。神经网络相对传统序列分析模型如ARIMA最有优势的地方在于——无需建立大量fine-tuned、针对序列的模型参数。

阅读更多

机器学习研究者所说的 Support Vector Machines 通常泛指最大边界分类器 (Maximal Margin Classifier)、支持向量分类器 (Support Vector Classifiers) 和支持向量机 (Support Vector Machine) 三者。其本质都是构造linear decision boundary,前者分别是后者在数据纬度和适用范围方面的延伸。

阅读更多

Review note for Pregel: A System for Large-Scale Graph Processing

Pregel Paper
Pregel Paper

1 - Summary Large graphs have been under analysing for years due to their ubiquity and commercial values, while the existing approaches have many limitations in terms of locality, efficiency, flexibility, etc. Google introduced a vertex-centric computational model framework in this paper that is suitable for large-scale graphs processing on clusters of numerous commodity computers in a manner that developers can easily program with an abstract API without concerning distribution-related details behind it. The paper describes Pregel, the large-scale graph processing model, and associated C++ API, discusses its implementation issues, applications to some algorithms, performances results, and also points out the future directions.

阅读更多

Your browser is out-of-date!

Update your browser to view this website correctly. Update my browser now

×