Overfitting

As explained in Deep Learning with R, Third Edition

Overfitting is a modeling condition in which performance is better on training data than on previously unseen data, including when repeated tuning adapts a model to validation data.

Overfitting happens when a model gets better at its training data without getting better at new data. A handwritten-digit classifier, for example, reached 98.9% training accuracy but 97.8% test accuracy. The goal is not the best training score; it is good generalization. section 2.1 section 5.1

Watch both sides of training

This R/Keras example keeps test images out of training and uses part of the training data for validation: library(keras3) .[.[train_images, train_labels], .[test_images, test_labels]] <- dataset_mnist() train_images <- array_reshape(train_images / 255, c(60000, 28 * 28)) test_images <- array_reshape(test_images / 255, c(10000, 28 * 28)) model <- keras_model_sequential() |> layer_dense(512, activation = "relu") |> layer_dense(10, activation = "softmax") model |> compile(optimizer = "adam", loss = "sparse_categorical_crossentropy", metrics = "accuracy") history <- model |> fit(train_images, train_labels, epochs = 20, batch_size = 128, validation_split = 0.2) plot(history) Compare training and validation loss across epochs. If training loss keeps falling while validation loss turns upward, further training is fitting patterns that do not transfer. Choose changes using validation results; reserve `evaluate(model, test_images, test_labels)` for assessing the final model on untouched data. section 2.1 section 4.1.4 section 5.2.1

A practical response depends on where the problem appears:

• If validation performance improves and then degrades, try fewer epochs. In a movie-review classifier, validation results peaked around epoch four even as training improved. section 4.1.4
• If the model cannot yet overfit, it may still lack capacity. Add layers, enlarge them, or train longer while monitoring both training and validation metrics. Once it can overfit, refine generalization with regularization or a smaller model. section 6.2.4 section 20.1.5
• Watch for misleading training patterns: invalid or mislabeled examples, ambiguous labels, and noisy features can draw a model toward behavior that performs poorly on new data. section 5.1.1
• Do not repeatedly tune against the test set. Even validation results can become misleading when many hyperparameter choices are made from them: information about that set leaks into the configuration. section 5.2.1 section 18.1.1

Figure 5.1 Canonical overfitting behavior

The canonical training curve helps locate the turning point where continued training stops improving generalization. section 5.1.1

How Deep Learning with R, Third Edition covers it

How deep it goes

Explains the training-versus-validation trajectory, noisy-data risks, deliberate capacity testing, and validation leakage without formal derivations.

Examples

Uses an MNIST training–test accuracy gap and IMDb training and validation curves.

What it assumes

Introduces overfitting with a first neural network, then develops it through classification examples and dataset splits.

What you can do after

Diagnose/debug with it by comparing training and validation metrics, adjusting epochs or capacity, and protecting final test evaluation.

How it connects

Connects optimization, generalization, underfitting, model capacity, regularization, and hyperparameter tuning.

liveBookmanning.com

Read Deep Learning with R, Third Edition on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Grokking Machine LearningOverfitting is a modeling condition in which a model captures noise or idiosyncrasies in training data and generalizes poorly to new data.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionThe failure mode where performance improves on training data while degrading on unseen data because the model has adapted too specifically to the training set.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA failure mode where a model memorizes irrelevant details of the training data and generalizes poorly, discussed here as a risk of increased capacity.
• 

  liveBookmanning.com
  Causal Inference for Data ScienceOverfitting is the condition in which a model captures noise or idiosyncrasies in training data and consequently generalizes poorly to new data.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionOverfitting is a modeling failure in which a model relies too heavily on peculiarities of its training data and performs poorly on new data.
• 

  liveBookmanning.com
  Math and Architectures of Deep LearningA training failure mode in which a model fits idiosyncrasies of the training data too closely and generalizes poorly.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionOverfitting is a condition in which a model matches training data too closely and performs poorly on varied unseen data.
• 

  liveBookmanning.com
  Ensemble Methods for Machine LearningOverfitting is a modeling failure in which a model fits training data too closely and does not necessarily generalize well to new data.
• 

  liveBookmanning.com
  The AI Pocket BookA failure mode in which a model becomes too specialized to its training data and generalizes poorly to new cases.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA training failure mode where the model memorizes training data too closely and generalizes poorly to new inputs.
• 

  liveBookmanning.com
  Data Without LabelsOverfitting is a modeling condition in which a supervised learning model performs well on training data but less accurately on unseen data.
• 

  liveBookmanning.com
  Investing for ProgrammersOverfitting is a modeling failure in which a model captures irrelevant variation in training features and fails to generalize reliably to new data.
• 

  liveBookmanning.com
  Generative AI in ActionOverfitting is a modeling condition in which learned patterns fit training data too closely and fail to generalize well to new examples.
• 

  liveBookmanning.com
  Machine Learning System DesignA condition in which a model fits its training data too closely and performs poorly on unseen data because it captures insignificant or non-generalizable patterns.
• 

  liveBookmanning.com
  Starting Data Analytics with Generative AI and PythonOverfitting is a modeling failure in which a model fits noise or sample-specific variation rather than generalizable underlying patterns.
• 

  liveBookmanning.com
  Demand Forecasting Best PracticesOverfitting is a modeling condition in which a model fits historical data well but fails to generalize to future or otherwise unseen data.
• 

  liveBookmanning.com
  Sutskever's ListOverfitting is a modeling failure in which a model fits training data too closely and performs poorly on unseen data.
• 

  liveBookmanning.com
  Statistics Every Programmer NeedsOverfitting is a modeling condition in which a model captures idiosyncrasies of the fitting data at the expense of performance on new data.
• 

  liveBookmanning.com
  LLMs in ProductionOverfitting is a condition in which a model becomes excessively tailored to training data and performs poorly on unseen data.
• 

  liveBookmanning.com
  Graph Neural Networks in ActionA modeling failure mode in which a model fits training data patterns too closely and generalizes poorly to validation or unseen data.
• 

  liveBookmanning.com
  Reinforcement Learning from Human FeedbackOverfitting is a training condition in which a model fits its training data or objective too closely and generalizes poorly.
• 

  liveBookmanning.com
  Building Reliable AI SystemsA model-training outcome in which a model fits training examples too closely and generalizes poorly to new data.
• 

  liveBookmanning.com
  Financial AI in PracticeOverfitting occurs when a model captures patterns specific to its training data that do not generalize reliably to new data.

Compare how 24 books explain overfitting →

Related concepts

• regularizationaddressed by · Regularization is a modeling technique that constrains or penalizes solutions during fitting or optimization to discourage undesirable complexity or behavior and improve generalization or estimation.
• dropoutaddressed by · Dropout is a neural-network regularization technique that randomly suppresses units, connections, or activations during training to reduce overfitting.
• early stoppingaddressed by · Early stopping is a technique that terminates an iterative process before its planned completion when a specified condition indicates that further work is unnecessary or unlikely to improve the objective.
• underfittingcontrasts with · 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.
• failure modekind of · A failure mode is a distinct way in which a system, component, process, or operation can fail or produce an undesirable result.
• tree pruningaddressed by · Tree pruning is the removal of decision-tree branches that fail a specified split-quality condition.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with R, Third Edition. The section links point to the parts of the book it draws on.