- TensorFlow Machine Learning Projects
- Ankit Jain Armando Fandango Amita Kapoor
- 157字
- 2021-06-10 19:15:33
TensorFlow boosted trees estimator
TensorFlow Boosted Trees (TFBT) is an improved scalable ensemble model built on top of generic gradient boosting trees.
Google published the details of the TensorFlow boosted trees implementation in the following paper: A scalable TensorFlow based framework for gradient boosting by Natalia Ponomareva, Soroush Radpour, Gilbert Hendry, Salem Haykal, Thomas Colthurst, Petr Mitrichev, Alexander Grushetsky, presented at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) 2017 . The paper is available at the following link: http://ecmlpkdd2017.ijs.si/papers/paperID705.pdf.
The gradient boosting algorithm is implemented by various libraries such as sklearn, MLLib, and XGBoost. TensorFlow's implementation is different from these implementations as described in the following table extracted from the TFBT research paper:
TFBT Research Paper from Google
The TFBT model can be extended by writing custom loss functions in TensorFlow. The differentiation for these custom loss functions is automatically provided by TensorFlow.
推薦閱讀
- Mastering Mesos
- 數(shù)據(jù)中心建設(shè)與管理指南
- 空間傳感器網(wǎng)絡(luò)復(fù)雜區(qū)域智能監(jiān)測技術(shù)
- Pig Design Patterns
- JSP從入門到精通
- 工業(yè)機(jī)器人操作
- Learn Microsoft Azure
- 新一代人工智能與語音識別
- Effective Business Intelligence with QuickSight
- Moodle 2.0 Course Conversion（Second Edition）
- Flash CS5二維動畫設(shè)計與制作
- 新世紀(jì)Photoshop CS6中文版應(yīng)用教程
- 工業(yè)機(jī)器人技術(shù)
- Spark Streaming實時流式大數(shù)據(jù)處理實戰(zhàn)
- Mastering Android Game Development with Unity