Data augmentation

As explained in Deep Learning with JAX

The practice of creating modified training examples to increase diversity and improve model robustness.

Need more varied training data without collecting more images? Data augmentation creates modified examples, such as noisy or rotated images, to improve robustness and reduce overfitting. section 9.1

A practical image-classification augmentation setup can:

• Add random noise to existing training images. section 9.1
• Apply random rotations to increase dataset diversity. section 9.1
• Use JAX's functional random-number keys rather than hidden mutable generator state. section 9.0

Noisy and rotated images

Imagine training an image classifier. Randomly adding noise and rotating each image produces varied training examples, helping the network become more robust while acting as implicit regularization. section 9.1

Figure 9.1 Scheme of the data augmentation process

Use the process diagram to visualize how original images become varied training examples. section 9.1

How Deep Learning with JAX covers it

How deep it goes

Explains augmentation through two image transformations and connects it to implicit regularization and random-number handling.

Examples

Demonstrates image classification with random noise and random rotations applied to training images.

What it assumes

Assumes image-classification training and introduces augmentation through random noise and rotations.

What you can do after

Apply data augmentation with JAX's functional random-number model to diversify image-classification training data.

How it connects

Links data augmentation to random numbers, implicit regularization, overfitting, and functional programming.

liveBookmanning.com

Read Deep Learning with JAX on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Deep Learning with R, Third EditionData augmentation is a technique that generates additional training examples by applying label-preserving transformations to existing data.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA training technique that creates modified versions of examples to increase effective dataset diversity while preserving task-relevant meaning.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA regularization approach that creates additional training examples by applying label-preserving random transformations to existing samples.
• 

  liveBookmanning.com
  Delivering Machine Learning Projects: From design to deploymentData augmentation is the creation of additional training examples by applying transformations or alterations to existing data.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIA technique that expands or diversifies training data by applying label-preserving transformations or generating additional examples.
• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsThe practice of creating additional training examples by applying label-preserving transformations to existing data.
• 

  liveBookmanning.com
  Generative AI in ActionData augmentation is the creation or transformation of training examples to increase dataset variety while preserving task-relevant information.
• 

  liveBookmanning.com
  Sutskever's ListData augmentation is the creation of varied training examples by applying label-preserving transformations to existing data.

Compare how 9 books explain data augmentation →

Related concepts

• AlexNetused by · AlexNet is a convolutional neural network architecture designed for image classification and recognized for its landmark performance in large-scale image recognition.
• overfittingaddresses · 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.
• training datasetproduces · A collection of examples or observations supplied to a learning procedure to fit or adapt a model or learn its patterns or parameters.
• demonstrationuses · A demonstration is an example pairing an input, request, or prompt with a corresponding output, answer, or label to illustrate a task or expected behavior.
• lax.switchuses · A JAX control-flow primitive that selects one branch from multiple alternatives based on an integer index.
• regularizationkind of · 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.

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