The talk opens by providing a sketch of machine learning and how it relates to functional programming.
We subsequently introduce ONNX and motivate the use of an interchange format and a dedicated serving/prediction layer for production.
Next we cover ONNX-Scala’s design goals and features, discussing backends, the generated fine-grained API, and model code generation.
Along the way we compare an ONNX model visualization with the representation of the model in ONNX-Scala.
This is followed by a discussion of the type-safe/functional features offered by ONNX-Scala and some remarks on future directions.