The talk will open by providing a sketch of machine learning and ONNX/ONNX-Scala and motivating the use of an interchange format and a dedicated serving/prediction layer for production. This will be followed by a discussion of the type-safe/functional features offered by ONNX-Scala and some remarks on performance.
Next we will briefly introduce at a high level an example machine learning model in the context of a specific use case. Finally, we will walk through a full pipeline deployment from training (in one of several deep learning frameworks) to prediction/serving (in ONNX-Scala) for this model.