Setting up your Watson Studio project for machine learning
To design, train, and deploy machine learning models in IBM Watson Studio, you need to associate an IBM Watson Machine Learning service instance, as well as some supporting services (such as IBM Cloud Object Storage) with a project.
Note: Watson Studio simplifies managing service instances, collaborating with teammates, as well as designing, training, and deploying models. This topic is about getting set up to work with machine learning in Watson Studio. To get set up to work with Watson Machine Learning without using Watson Studio, see: Using the IBM Cloud dashboard.
How to set up a project for machine learning depends on your situation:
- Do you want to create a new project or reuse an existing project?
- Do you want to create a new Watson Machine Learning service instance or reuse one you already have?
Follow the instructions that match your situation.
- Click the IBM Watson link in the header to navigate to the Watson Studio home panel.
- Click New project.
- Choose a project type:
- If you want to train complex neural networks using experiments, choose a "Deep Learning" project
- For all other machine learning work, choose the "Modeler" project type
- If you don't already have any of the required services, such as Watson Machine Learning and IBM Cloud Object Storage, new service instances are created.
This video demonstrates creating a new project for working with Watson Machine Learning:
- From the Settings page of your project in Watson Studio, click Add service.
- Choose Machine Learning.
- Click the New option to create a new instance of the Watson Machine Learning service, or click the Existing option to select an existing instance.
Note: You can only associate a Watson Machine Learning service instance with your project when the Watson Machine Learning service instance and the Watson Studio instance are located in the same region.
- Model builder: Build a model with step-by-step instructions
- Flow editor: Design a more complex model using Spark MLlib nodes, SPSS Modeler nodes, or neural network nodes
- Experiment builder: Create an experiment to train a complex neural network
- Notebooks: Code in Python, R, or Scala with AI frameworks
- Command-line interface: Work from your local environment