DIGIT RECOGNITION

In this study we analyze and apply several machine learning techniques for digit recognition (classification) on the MNIST digits data - Modified National Institute of Standards and Technology database digits.

​

The MNIST dataset is a very well known database of 70 thousands handwriting images of the 10 digits, each one consisting of 784 pixels, being 28 x 28 pixels images. It is also available in Python, for Machine Learning analysis.

​

The techniques will create models through the training set and classify the test set digits based on their conditional probability.

​

We continue the study in the next session, where we apply dimension reduction on the dataset and fit their models.