End-to-end learning
End-to-end learning is a training approach that jointly learns a complete model or connected pipeline to map inputs to outputs under a shared objective.
Retrieval Augmented Generation, The Foundational Ideas
End-to-end training jointly optimizes connected system components by propagating learning signals through the complete input-to-output pipeline.
- How it is used
- Aligns retrieval with answer production when similarity ranking favors lookalike passages over useful evidence.
- How deep it goes
- Works through masked-token and reader-likelihood training signals, compares retriever losses, and leaves full-pipeline optimization as an open problem.
- Examples
- Uses a masked butterfly-migration sentence and a margin-decline question whose answer lies in explanatory commentary.
- What you can do after
- Evaluate/understand when reader-guided retriever training warrants its cost compared with a fixed-retriever pipeline.
Read how Retrieval Augmented Generation, The Foundational Ideas explains end-to-end learning →
Sutskever's List
End-to-end training is a training approach that learns a complete mapping from raw inputs to outputs without separately engineered intermediate representations.
- How it is used
- Uses learned mappings from raw inputs to outputs to replace separately engineered intermediate representations.
- How deep it goes
- Explains the approach conceptually through a landmark result rather than detailing architecture, optimization, or training mechanics.
- Examples
- Uses AlexNet’s 2012 ImageNet and ILSVRC victory as its central example.
- What you can do after
- Evaluate why end-to-end neural training became a turning point in computer vision.
Optimization Algorithms: AI techniques for design, planning, and control problems
A learning approach that trains a model to map inputs directly to desired outputs with minimal separately engineered intermediate stages.
- How it is used
- Directs machine learning to formulate solutions for combinatorial optimization problems from their input instances.
- How deep it goes
- Defines direct formulation and contrasts two alternatives, but stops short of detailing training procedures or implementation.
- Examples
- Uses pointer networks trained and validated on differently sized Euclidean planar symmetric traveling-salesperson instances.
- What you can do after
- Evaluate direct solution formulation against learned algorithm configuration and repeatedly model-guided optimization.
Timeless Algorithms, The Foundational Ideas
End-to-end learning is an approach in which a single objective guides the joint learning of parameters throughout a model.
- How it is used
- Guides joint parameter learning throughout a neural network using one loss function.
- How deep it goes
- Traces prediction, loss, backpropagated gradients, parameter updates, and inference, without detailing specific optimization algorithms.
- Examples
- Uses pixels, sensor readings, customer features, and word embeddings, alongside regression and classification outputs and losses.
- What you can do after
- Understand how a single loss connects network predictions to representation learning and parameter updates.
Read how Timeless Algorithms, The Foundational Ideas explains end-to-end learning →
Also covered in
What to know first
- backpropagationBackpropagation is reverse-mode differentiation that propagates derivatives backward through a computational graph to compute gradients of an output or loss with respect to inputs and parameters.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- similarity searchSimilarity search is a retrieval technique that finds or ranks items by their similarity to a query, often by comparing feature or vector representations under a similarity or distance measure.
- classifierA classifier is a predictive model that assigns an input to one or more discrete classes or categories.
Related concepts
- Deep Speech 2used by · Deep Speech 2 is a large-scale neural speech-recognition system designed for end-to-end automatic speech recognition.
- Retrieveruses · A retriever is a software component that searches or queries an information source and returns items relevant to a query for use by downstream processes.
- objective functionuses · An objective function is a mathematical function that assigns values to candidate solutions or parameter settings, which an optimization procedure seeks to minimize or maximize.
- REALM++uses · REALM++ is a method for improving REALM through changes to training scale, retrieval during evaluation, and supervision without changing its model architecture.
- modularitycontrasts with · Modularity is the organization of a system into separable components with distinct responsibilities and defined interactions.
- Atlasused by · Atlas is a retrieval-augmented language model designed for knowledge-intensive natural-language tasks.
Questions about end-to-end learning
What is end-to-end learning?
End-to-end learning is a training approach that jointly learns a complete model or connected pipeline to map inputs to outputs under a shared objective.
Which Manning books explain end-to-end learning?
Retrieval Augmented Generation, The Foundational Ideas, Sutskever's List, Optimization Algorithms: AI techniques for design, planning, and control problems and Timeless Algorithms, The Foundational Ideas.
What should I know before learning end-to-end learning?
Manning books that teach end-to-end learning usually introduce backpropagation, language model, similarity search and classifier first.
What is the difference between end-to-end learning and modularity?
End-to-end learning is a training approach that jointly learns a complete model or connected pipeline to map inputs to outputs under a shared objective. Modularity is the organization of a system into separable components with distinct responsibilities and defined interactions.
What is end-to-end learning also called?
End-to-end learning is also called end-to-end training.
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.



