The MNIST database (Modified National Institute of Standards and Technology database) is a large database of handwritten digits that is commonly used for training various image processing systems. The database is also widely used for training and testing in the field of machine learning. It was created by "re-mixing" the samples from NIST's original datasets. The MNIST database of handwritten digits, available from this page, has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger set available from NIST.
This dataset can be considered as a Hello World! programme in the machine learning realm. As they say,
A learning model is only as good and/or bad as the data.
The digits in MNIST dataset have been size-normalized and centered in a fixed-size image. It is a good database for people who want to try learning techniques and pattern recognition methods on real-world data while spending minimal efforts on preprocessing and formatting.
As a newbie myself, I have had helped from different sources mostly from this and that sources. You can read the article I wrote while working on this Digit Recognizer using MNIST dataset
Prediction: Here is the prediction on the test class.
