End-to-end model
An end-to-end model jointly learns the transformation from inputs to final outputs, including intermediate representations, within a single modeling pipeline.
Machine Learning System Design
A model architecture that maps inputs directly to final outputs without explicit intermediate representations or manually designed processing stages.
- How it is used
- Uses a single learned model to replace multi-stage machine learning pipelines when manual decomposition limits the solution.
- How deep it goes
- Compares architectural rationale and a TTS example, but stops short of training procedures, implementation details, and model internals.
- Examples
- Uses text-to-speech conversion and direct text-to-audio waveform synthesis as the central architectural comparison.
- What you can do after
- Evaluate when direct learned mappings offer advantages over decomposed pipelines and recognize their knowledge, cost, and reliability limits.
Read how Machine Learning System Design explains end-to-end model →
Graph Neural Networks in Action
A model that jointly learns intermediate representations and task predictions during a single training process.
- How it is used
- Trains graph representations and node-label predictions together for graph classification.
- How deep it goes
- Explains data preparation, architecture changes, masked optimization, and embedding inspection, but not deeper training theory.
- Examples
- Compares two- and four-layer GNNs using randomized or N2V node features on the books_gml graph.
- What you can do after
- Build it from scratch with PyTorch Geometric, train masked node classifiers, and inspect learned embeddings alongside predictions.
Read how Graph Neural Networks in Action explains end-to-end model →
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.