- Learn Amazon SageMaker
- Julien Simon;Francesco Pochetti
- 274字
- 2021-04-09 23:11:22
Chapter 3: AutoML with Amazon SageMaker Autopilot
In the previous chapter, you learned how Amazon SageMaker helps you build and prepare datasets. In a typical machine learning project, the next step would be to start experimenting with algorithms in order to find an early fit and get a sense of the predictive power you could expect from the model.
Whether you work with statistical machine learning or deep learning, three options are available when it comes to selecting an algorithm:
Write your own, or customize an existing one. This only makes sense if you have strong skills in statistics and computer science, if you're quite sure that you can do better than well-tuned, off-the-shelf algorithms, and if you're given enough time to work on the project. Let's face it, these conditions are rarely met.
Use a built-in algorithm implemented in one of your favorite libraries, such as Linear Regression or XGBoost. For deep learning problems, this includes pretrained models available in TensorFlow, PyTorch, and so on. This option saves you the trouble of writing machine learning code. Instead, it lets you focus on feature engineering and model optimization.
Use AutoML, a rising technique that lets you automatically build, train, and optimize machine learning models.
In this chapter, you will learn about Amazon SageMaker Autopilot, an AutoML capability part of Amazon SageMaker. We'll see how to use it in Amazon SageMaker Studio, without writing a single line of code, and also how to use it with the Amazon SageMaker SDK:
Discovering Amazon SageMaker Autopilot
Using Amazon SageMaker Autopilot in SageMaker Studio
Using Amazon SageMaker Autopilot with the SageMaker SDK
Diving deep on Amazon SageMaker Autopilot
- 一本書學(xué)內(nèi)部審計:新手內(nèi)部審計從入門到精通
- 中國新股民必讀手冊(2015年最新版)
- 自愿審計動機與質(zhì)量研究:基于我國中期財務(wù)報告審計的經(jīng)驗證據(jù)
- 資本的眼睛
- 陜西文物年鑒·2015
- 基本有用的計量經(jīng)濟學(xué)
- 非線性經(jīng)濟關(guān)系的建模
- Microsoft System Center Data Protection Manager 2012 SP1
- 《企業(yè)內(nèi)部控制基本規(guī)范》合規(guī)實務(wù)指南
- 行政單位經(jīng)濟責(zé)任審計實務(wù)指南
- 內(nèi)審兵法
- 計量經(jīng)濟學(xué)
- Oracle E-Business Suite Financials R12:A Functionality Guide
- QlikView for Developers Cookbook
- 統(tǒng)計學(xué)視角下的金融高頻數(shù)據(jù)挖掘理論與方法研究