1. Introduction to Watson Studio and Watson Machine Learning for Cloud Pak for Data
- Describe the IBM Cloud Pak for Data platform and AI
- Describe the four rungs in the ladder to AI
- Describe the personas on the platform
- Describe how to collaborate on the platform
- Describe the CRISP-DM methodology
2. Work with analytics projects
- Describe analytics projects
- Create analytics projects
- Leverage industry accelerators
3. Import data
- Identify key concepts in working with data
- Describe correct column types
- Add local files to the project
- Created connections
- Add connected data sets to the project
4. Prepare data for modeling with Data Refinery
- Identify three tasks in preparing data for modeling
- Describe the capabilities of Data Refinery
- Describe steps, flows, and jobs
- Join data
- Profile data
- Visualize data
5. Automate building supervised models with AutoAI experiment
- Describe when AutoAI experiment can be used
- Describe the importance of column types
- Describe how the best model is identified
- Describe pipelines
- Save AutoAI experiment pipelines to the project
- Explain evaluation measures
6. Work with notebooks
- Work with notebooks
- Load data into a notebook
- Prepare data for modeling
- Build machine learning models
- Save machine learning models to the project
7. Deploy Watson Machine Learning models
- Identify Watson Machine Learning models
- Describe deployment spaces
- Create deployment spaces
- Describe model deployment options
- Create deployments
- Test deployments