- Hands-On Machine Learning with ML.NET
- Jarred Capellman
- 90字
- 2021-06-24 16:43:35
Loss function
This property uses the loss function set when the regression trainer was initialized. In the case of our linear regression example application, we used the default constructor, which for SDCA is defaulted to the SquaredLoss class.
Other regression loss functions offered by ML.NET are the following:
- TweedieLoss (used for Tweedie regression models)
- PoissonLoss (used for Poisson regression models)
The idea behind this property is to allow some flexibility when it comes to evaluating your model compared to the other four properties that use fixed algorithms for evaluation.
推薦閱讀
- Java應用開發與實踐
- 樂高機器人設計技巧:EV3結構設計與編程指導
- 網頁設計與制作教程(HTML+CSS+JavaScript)(第2版)
- Web Application Development with MEAN
- C++程序設計基礎教程
- The Complete Coding Interview Guide in Java
- Windows Phone 7.5:Building Location-aware Applications
- Web程序設計:ASP.NET(第2版)
- Hands-On Robotics Programming with C++
- 多媒體技術及應用
- Java EE項目應用開發
- TypeScript全棧開發
- C# 10核心技術指南
- C#從入門到精通(微視頻精編版)
- Python High Performance(Second Edition)