Core ML doesn't provide a way to train your own models. You only can convert existing ones to Apple 'mlmodel' format.
To create your own neural networks, use Caffe or Keras frameworks and then convert those models to CoreML format. For traditional machine learning algorithms Core ML is also compatible with Scikit-learn* and XGBoost.
You can also train and run neural networks on iOS without Core ML, just use Caffe 2 or TensorFlow. I support a long list of iOS-compatible machine learning libraries, if you're interested.
All libraries mentioned above have a great documentation and a lot of tutorials for you to start creating your own models.
*LibSVM is also compatible, but scikit-learn uses it under the hood anyway.
