Underfitting
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.
Grokking Machine Learning
A model whose complexity is insufficient to capture the relevant structure of its dataset.
- How it is used
- Frames underfitting as a training problem and guides model selection through testing, validation, and complexity comparison.
- How deep it goes
- Defines insufficient complexity, demonstrates it with polynomial regression, and diagnoses it through training, testing, and validation errors.
- Examples
- Uses an exam analogy, polynomial models of degrees 1, 2, and 10, error comparisons, and a model-selection exercise.
- What you can do after
- Diagnose underfitting by comparing training with testing or validation error and select a more suitable model complexity.
Machine Learning System Design
A condition in which a model is too simple to capture important relationships between features and the target variable, resulting in poor performance on both training and new data.
- How it is used
- Uses learning-curve analysis to diagnose whether poor performance reflects high bias, insufficient data, or excessive variance.
- How deep it goes
- Defines high bias and contrasts it with overfitting, then provides curve-based remedies without deriving model internals.
- Examples
- Uses training–validation curves and an augmented-reality footwear detector that mistakes pet paws and toys for feet.
- What you can do after
- Diagnose underfitting from converged, high-loss curves and choose greater model complexity instead of collecting more data.
Read how Machine Learning System Design explains underfitting →
Generative AI in Action
Underfitting is a modeling condition in which a model fails to learn enough structure from its training data to perform well on new examples.
- How it is used
- Guides fine-tuning monitoring by identifying when a model has not learned enough task-relevant structure.
- How deep it goes
- Interprets training and validation loss patterns, discusses training duration and data adequacy, and uses no mathematical derivation.
- Examples
- Uses GPT-3.5 Turbo training-loss curves and monitored dataset adjustments as concrete diagnostic examples.
- What you can do after
- Diagnose underfitting with training and validation loss, then evaluate whether more training or dataset changes are warranted.
Grokking AI Algorithms, Second Edition
Underfitting is a condition in which a model is too simple or insufficiently trained to perform well even on its training data.
- How it is used
- Diagnoses whether a machine-learning model has learned too little, memorized training data, or generalized useful patterns.
- How deep it goes
- Defines underfitting through contrasts and an analogy, then stops short of prescribing a specific remedy.
- Examples
- Uses an exam-study analogy, incorrect classifications, training accuracy, unseen-data performance, and a fit-comparison figure.
- What you can do after
- Evaluate model fit by comparing training performance with performance on new, unseen data.
Read how Grokking AI Algorithms, Second Edition explains underfitting →
Deep Learning with R, Third Edition
Underfitting is a modeling condition in which a model is too simple or insufficiently trained to capture patterns needed for good performance.
- How it is used
- Uses underfitting as an early training diagnosis and as a guide for increasing model capacity before refining generalization.
- How deep it goes
- Explains training-loss and validation-loss patterns, then gives capacity-scaling steps without mathematical derivation.
- Examples
- Uses MNIST, logistic regression, training curves, trivial baselines, and progressively larger neural networks as examples.
- What you can do after
- Diagnose underfitting from loss and metric trends, then increase layers, layer size, or training duration to test model capacity.
Read how Deep Learning with R, Third Edition explains underfitting →
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
Underfitting is a modeling failure in which a model is too simple to capture important patterns in the data.
- How it is used
- Uses a simple baseline to reveal weak fit, missed structure, and directions for subsequent model development.
- How deep it goes
- Diagnoses underfitting through cross-validation predictions, metrics, plots, infeasible outputs, and coefficient inspection.
- Examples
- Uses a listing-price regression baseline, flat prediction plot, negative predictions, error metrics, and case-level coefficient contributions.
- What you can do after
- Diagnose/debug with cross-validation predictions, evaluation metrics, plots, prediction ranges, and coefficient contributions.
Read how Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI explains underfitting →
The AI Pocket Book
A failure mode where a model is too simple to capture the training pattern and performs poorly.
- How it is used
- Distinguishes a model that fails to learn the task from one that memorizes training examples.
- How deep it goes
- Defines underfitting through its contrast with overfitting, but stops short of discussing diagnosis or remedies.
- Examples
- Contrasts performance on training data with performance on new sentences and images.
- What you can do after
- Evaluate whether a model’s learned process is too simple to work on training and unseen data.
Related concepts
- overfittingcontrasts with · 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.
- genetic algorithmaddressed by · A genetic algorithm is an evolutionary optimization method that improves a population of candidate solutions through fitness-based selection and variation, often including recombination and mutation.
- bias-variance tradeoffcontrasts with · The bias-variance tradeoff is the balance between systematic error from restrictive model assumptions and error from sensitivity to variation in sampled data.
- learning curvemeasured by · A learning curve is a representation of how performance or proficiency changes as experience, training progress, or training data increases.
- expressive poweraddresses · Expressive power is the capacity of a model, language, or system to represent or convey a range and complexity of functions, patterns, distinctions, or ideas.
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.