mnist


mnist, a keras script which sets up a neural network to classify each image of a numeric digit in the MNIST dataset into one of 10 categories: "0", "1", ..., "9".

Licensing:

The computer code and data files described and made available on this web page are distributed under the GNU LGPL license.

Related Data and Programs:

boston_housing, a keras script which sets up a neural network to apply regression to predict housing prices, based on the Boston housing dataset.

boston_housing_external, a keras script which reads the Boston housing dataset from an external file, rather than referencing the built-in keras dataset, and applies regression to predict housing prices

hourly_wages, a keras script which uses a neural network to create a multivariable regression model from a set of hourly wage data.

mnist_convnet, a keras script which sets up a convolutional neural network to classify the MNIST digit image data.

movie_review, a keras script which sets up a neural network to classify movie reviews from the IMDB database.

newswire, a keras script which sets up a neural network for the classification of Reuters newswire texts into one of 46 categories.

regression_1d, a keras script which reads training and test files of data pairs (x,y), and seeks a regression formula y = b + w * x.

Author:

The original text is by Francois Chollet; some modifications were made by John Burkardt.

Reference:

  1. Francois Chollet,
    Deep Learning with Python,
    Manning, 2018,
    ISBN: 9781617294433.

Source Code:


Last revised on 18 April 2019.