How deeply does Sutskever's List cover data augmentation?

Distinguishes geometric transforms from PCA-based color jitter and their purposes, without specifying implementation parameters.

Data augmentation

As explained in Sutskever's List

Data augmentation is the creation of varied training examples by applying label-preserving transformations to existing data.

Data augmentation creates varied training examples by transforming existing data while preserving its labels. In AlexNet, it expanded ImageNet’s effective size and diversity, helping the network generalize despite having 60 million parameters and training on 1.2 million images. section 2.5.3

AlexNet used two kinds of transformations:

Random crops and horizontal reflections exposed the network to objects in different positions or orientations. section 2.5.3
PCA-based color jitter perturbed RGB values to simulate changes in brightness, contrast, and color balance. section 2.5.3

These transformations simulated realistic variability and noise. Combined with dropout, they helped AlexNet mitigate overfitting; augmentation was one of several optimization-aware choices assembled into the system. section 2.5.3 section 2.5.5

How Sutskever's List covers it

liveBook manning.com

Read Sutskever's List on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

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

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

Deep Learning with JAXThe practice of creating modified training examples to increase diversity and improve model robustness.
liveBook manning.com

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

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

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 Sutskever's List. The section links point to the parts of the book it draws on.