How do I use machine learning on iPad?

To use machine learning on an iPad, you can leverage Apple's machine learning frameworks and tools, which are designed to run efficiently on Apple devices, including iPads. Here are some steps and tools you can use:

Core ML: This is the primary framework for running machine learning models on Apple devices. It allows you to integrate machine learning models into your app and optimizes them for hardware-accelerated execution across the CPU, GPU, and neural engine. You can convert models from other formats using Core ML tools and optimize them for performance.
Create ML: This tool allows you to train and customize machine learning models using your own data. It provides templates for various tasks, making it easy to train, evaluate, and iterate on models. Create ML is available on macOS, but the models you create can be deployed on iPadOS.
ML-powered APIs: Apple provides APIs that are powered by machine learning models, which you can use to add intelligent features to your app without needing to train your own models.
Optimizing Models: You can use Core ML tools to optimize your models for Apple hardware, employing techniques like quantization and efficient key-value caching for large language models.
Running Models on Device: Once your model is ready, you can integrate it into your app using Core ML, which will handle the execution of the model on the device.

For more detailed guidance, you can refer to the session Explore machine learning on Apple platforms, which covers running models on devices and other related topics.