Learning curve
A learning curve is a representation of how performance or proficiency changes as experience, training progress, or training data increases.
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
- Guides early error analysis by checking convergence and generalization before deeper investigation.
- How deep it goes
- Defines three curve types and gives plotting procedures and diagnostic patterns, without deriving learning algorithms.
- Examples
- Uses oscillating and exploding loss, diverging training and validation curves, and image-search loss components.
- What you can do after
- Diagnose/debug with it to choose whether to inspect training, adjust complexity, examine the data split, or gather more data.
Read how Machine Learning System Design 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 →
Related concepts
- training datasetuses · A collection of examples or observations supplied to a learning procedure to fit or adapt a model or learn its patterns or parameters.
- evaluation datasetuses · An evaluation dataset is a collection of examples or test cases, often with expected or judged outcomes, designated to assess a model or system against defined criteria.
- objective functionmeasures · An objective function assigns values to candidate solutions, predictions, or parameter settings according to a criterion to be minimized or maximized.
- overfittingmeasures · Overfitting is a modeling condition in which a model fits patterns or idiosyncrasies in its training data too closely and consequently generalizes poorly to new data.
- underfittingmeasures · A modeling failure in which insufficient capacity or training prevents a model from capturing relevant patterns in the data, resulting in poor performance even on training data.
- performancemeasures · Performance is the measurable effectiveness or operational behavior of a system under specified conditions, assessed through relevant qualities such as task results, speed, responsiveness, throughput, or resource use.
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.