impediment runconfig vs estimator

Author: nibaccam

articles/machine-learning/service/how-to-set-up-training-targets.md

@@ -48,7 +48,7 @@ Learn more about [submitting experiments](#submit) at the end of this article.
 
 ## What's an estimator?
 
-To facilitate model training using popular frameworks, the Azure Machine Learning Python SDK provides an alternative higher-level abstraction, the estimator class. This class allows you to easily construct run configurations. You can create and use a generic [Estimator](https://docs.microsoft.com/python/api/azureml-train-core/azureml.train.estimator?view=azure-ml-py) to submit training scripts that use any learning framework you choose (such as scikit-learn).
+To facilitate model training using popular frameworks, the Azure Machine Learning Python SDK provides an alternative higher-level abstraction, the estimator class.  This class allows you to easily construct run configurations. You can create and use a generic [Estimator](https://docs.microsoft.com/python/api/azureml-train-core/azureml.train.estimator?view=azure-ml-py) to submit training scripts that use any learning framework you choose (such as scikit-learn). We recommend using an estimator for training as it automatically contructs embedded objects like an environment or RunConfiguration objects for you. If you wish to have more control over how these objects are created and specfify what packages to install for your experiement run, follow [these steps](#amlcompute) to submit your training experiments using a RunConfiguration object on an Azure Machine Learning Compute.
 
 For PyTorch, TensorFlow, and Chainer tasks, Azure Machine Learning also provides respective [PyTorch](https://docs.microsoft.com/python/api/azureml-train-core/azureml.train.dnn.pytorch?view=azure-ml-py), [TensorFlow](https://docs.microsoft.com/python/api/azureml-train-core/azureml.train.dnn.tensorflow?view=azure-ml-py), and [Chainer](https://docs.microsoft.com/python/api/azureml-train-core/azureml.train.dnn.chainer?view=azure-ml-py) estimators to simplify using these frameworks.