articles » current » tools » number-recognition

"Supervised" Machine Deep Learning: Number Recognition

Artificial intelligence that recognizes hand-written numbers zero to nine using a neural network, learned from the MNIST database.

Supervised learning is a machine learning paradigm for problems where the available data consists of labeled examples, meaning that each data point contains features (covariates) and an associated label. The goal of supervised learning algorithms is learning a function that maps feature vectors (inputs) to labels (output), based on example input-output pairs.

See the code behind this. Also, see cat/dog image recognition and unsupervised learning example.

Draw a single digit from 0 to 9 and submit it to see if the computer can recognize it. Your hand-written numbers are saved and will be used to train the artificial intelligence.

0 to 9

This site uses cookies. Cookies are simple text files stored on the user's computer. They are used for adding features and security to this site. Read the privacy policy.