Deep Learning Practical 2: Decoding MNIST

August 04, 2016

MNIST (Mixed National Institute of Standards and Technology) is a database of handwritten digits. Compiled by Yann LeCun and colleagues, it’s a classic benchmark problem in machine learning. Pleasingly, you can write a model in Tensorflow that does a decent job of decoding the digits.

Having got to grips with Python and some of the Tensorflow fundamentals, we cannibalised the official Tensorflow tutorial 3 (‘MNIST from scratch’) to make an easy-to-follow tutorial for cracking MNIST using a simple feedforward network. If this is your first time with TF, you might find the Tensorflow Tutorial 1 a better starting point.

We go through the following steps:

  1.  Import the data
  2.  Look at the data
  3.  Figure out normalization
  4.  Compile training, validation, and test sets
  5.  Define model in Tensorflow
  6.  Run the model without training
  7.  Train and test
  8.  Evaluate performance

Download the iPython notebook here.

Any questions or corrections, give me a shout.


© 2023, Built with Gatsby