This code was entered into a Kaggle competition for recognizing digits in the MNIST dataset.
From the Kaggle competition page:
MNIST ("Modified National Institute of Standards and Technology") is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike.
My neural network achieved a score of 0.95780 when it was run on Kaggle's test data.
In neural-network.py
there is a method called trainvalidate
which shows both validation and training error.