MNIST dataset
MNIST is a labeled dataset of 28-by-28-pixel grayscale images representing handwritten digits from zero through nine.
Bayesian Optimization in Action
The MNIST dataset is a labeled collection of handwritten digit images commonly used for machine-learning training and evaluation.
- How it is used
- Uses handwritten digit images as structured-data inputs for Gaussian-process learning and simulated regression.
- How deep it goes
- Defines pixel structure, demonstrates tensor preparation, and works through a 1,000-image Gaussian-process experiment.
- Examples
- Shows a handwritten five, a 784-element tensor, and a train-test experiment using 1,000 training and 500 test images.
- What you can do after
- Apply it via PyTorch and torchvision to load, normalize, flatten, visualize, and split handwritten-digit data for GP prediction.
Read how Bayesian Optimization in Action explains MNIST dataset →
Deep Learning with Python, Third Edition
A standard dataset of handwritten-digit images used for machine-learning experiments and examples.
- How it is used
- Grounds introductory neural-network classification experiments in a familiar, repeatable benchmark.
- How deep it goes
- Explains dataset contents, tensor representation, preprocessing, prediction, and evaluation, but not dataset construction or collection details.
- Examples
- Uses Keras loading code, array-shape inspection, a displayed digit, preprocessing steps, predictions, and test accuracy.
- What you can do after
- Apply it via Keras to load, inspect, preprocess, train on, predict with, and evaluate a digit-classification dataset.
Read how Deep Learning with Python, Third Edition explains MNIST dataset →
Inside Deep Learning: Math, Algorithms, Models
A classic handwritten-digit image dataset of 28×28 grayscale examples used here to illustrate image loading and tensor structure.
- How it is used
- Uses a small image dataset to demonstrate loading, visualization, tensor structure, and attention-based toy problems.
- How deep it goes
- Explains dataset loading, PIL conversion, normalization range, channel dimensions, visualization, stacking, and pixel shuffling.
- Examples
- Demonstrates digit images, grayscale and RGB-like tensors, combined channels, and randomly shuffled pixels.
- What you can do after
- Apply it via torchvision to download splits, convert images into tensors, inspect shapes, and visualize or manipulate examples.
Read how Inside Deep Learning: Math, Algorithms, Models explains MNIST dataset →
Deep Learning with R, Third Edition
MNIST is a dataset of grayscale 28-by-28 pixel images of handwritten digits labeled from 0 through 9.
- How it is used
- Supports handwritten-digit classification and serves as a standard check that neural-network algorithms work as expected.
- How deep it goes
- Defines image dimensions, class labels, array organization, and train-test roles, while deferring detailed model mechanics.
- Examples
- Uses Keras array loading, sample digit images, array structures, and corresponding training and test labels.
- What you can do after
- Operate Keras to load MNIST arrays for training a handwritten-digit classifier and evaluating predictions.
Read how Deep Learning with R, Third Edition explains MNIST dataset →
Deep Learning with JAX
A standard handwritten-digit image dataset used for machine learning experiments and evaluation.
- How it is used
- Uses handwritten-digit images as a practical multiclass classification task for introducing a JAX deep-learning workflow.
- How deep it goes
- Positions MNIST within data loading and model training, without detailing the dataset’s internal construction or format.
- Examples
- Shows handwritten-digit images and uses batches produced by a TensorFlow Datasets data loader.
- What you can do after
- Apply it via TensorFlow Datasets as batched input for training and evaluating a JAX classification model.
Related concepts
- language modeluses · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- benchmarkkind of · A benchmark is a defined task, dataset, workload, procedure, or reference measure used to assess or compare performance or capability under specified criteria or conditions.
- logistic regressionused by · Logistic regression is a statistical classification model that estimates categorical outcome probabilities by applying a logistic or softmax function to a linear combination of input features.
- image recognitionused by · Image recognition is the computational task of identifying or classifying objects, patterns, scenes, or other meaningful content in images.
- Fashion-MNISTalternative to · Fashion-MNIST is a labeled dataset of grayscale images representing ten categories of clothing and accessories for machine-learning training and evaluation.
- LeNetused by · LeNet is an early convolutional neural-network architecture designed primarily for handwritten-digit and character recognition.
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.