Learning curve
A learning curve is a curve or trend showing how performance or proficiency changes with experience, practice, training progress, or training-data size.
Machine Learning System Design
A curve showing how a model's loss changes across training progress or another ordered evaluation dimension.
- How it is used
- Uses learning curves during error analysis to guide iterative model improvements and check convergence and fit.
- How deep it goes
- Explains iteration-, model-, and sample-wise curves with construction steps, interpretation, and debugging actions.
- Examples
- Uses retail demand forecasting and text-to-image search designs to plan complexity, loss-component, and sample-size curves.
- What you can do after
- Diagnoses training problems and evaluates whether model complexity or additional data might improve performance.
Read how Machine Learning System Design explains learning curve →
Build AI Drug Discovery Pipelines
A learning curve is a diagnostic plot showing model performance or error as a function of training-set size.
- How it is used
- Diagnoses whether underperformance reflects bias, variance, or insufficient training data before changing the model or collecting more data.
- How deep it goes
- Explains train-test behavior across dataset sizes and stops short of prescribing a single model-selection rule.
- Examples
- Uses solubility-prediction learning curves comparing RANSAC and SVR with training and test mean squared error.
- What you can do after
- Diagnose whether more data, a more complex model, or regularization is the most appropriate next intervention.
Read how Build AI Drug Discovery Pipelines explains learning curve →
Graph Neural Networks in Action
A plot showing a model's performance measure, such as loss, across training epochs.
- How it is used
- Uses epoch-by-epoch training and validation losses to monitor learning, compare models, and identify overfitting.
- How deep it goes
- Interprets declining curves, divergence, and validation-loss minima, but defers overfitting remedies to later treatment.
- Examples
- Compares GCN and GraphSAGE curves, highlighting validation divergence near epoch 20 and selecting the lowest-validation-loss checkpoint.
- What you can do after
- Diagnose overfitting from plotted losses and retain the model checkpoint with the best validation performance.
Read how Graph Neural Networks in Action explains learning curve →
Also covered in
- Fight Fraud with Machine LearningIn early access (MEAP)
- LLM Customization and Fine-TuningIn early access (MEAP)
- Interview Speak
- Human-in-the-Loop Machine Learning: Active learning and annotation for human-centered AI
What to know first
- epochAn epoch is one complete pass through the training data during model training.
- overfittingOverfitting is a modeling condition in which a model adapts too closely to particular data, including its noise or idiosyncrasies, and consequently generalizes poorly to new data.
- class imbalanceClass imbalance is a condition in a classification dataset where classes have substantially unequal numbers of examples.
- accuracyAccuracy is the degree to which a result agrees with a specified truth, reference, or criterion, commonly measured as the proportion of evaluated predictions that are correct.
Related concepts
- training datasetuses · A training dataset is a collection of examples supplied to a learning procedure to fit or adapt a model’s parameters or behavior.
- objective functionmeasures · 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.
- evaluation datasetuses · An evaluation dataset is a collection of data or test cases used to assess a model or system against specified outcomes or criteria.
- overfittingmeasures · Overfitting is a modeling condition in which a model adapts too closely to particular data, including its noise or idiosyncrasies, and consequently generalizes poorly to new data.
- accuracymeasures · Accuracy is the degree to which a result agrees with a specified truth, reference, or criterion, commonly measured as the proportion of evaluated predictions that are correct.
- error analysispart of · Error analysis is the systematic examination of errors to identify their patterns, causes, effects, or implications for improvement.
Questions about learning curve
What is learning curve?
A learning curve is a curve or trend showing how performance or proficiency changes with experience, practice, training progress, or training-data size.
Which Manning books explain learning curve?
Machine Learning System Design, Build AI Drug Discovery Pipelines and Graph Neural Networks in Action.
What should I know before learning learning curve?
Manning books that teach learning curve usually introduce epoch, overfitting, class imbalance and accuracy first.
What is learning curve part of?
Learning curve is part of error analysis. Error analysis is the systematic examination of errors to identify their patterns, causes, effects, or implications for improvement.
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.


