articles » current » tools » cat-vs-dog-recognition

"Supervised" Machine Deep Learning: Cat vs. Dog Recognition

Use artificial intelligence to identify an image of a dog or cat.

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 handwritten number recognition and unsupervised learning example.

The neural network seems to have locked on to the eyes, because uploading an image of a cat with round eyes will show as a dog and uploading an image of a dog, or even a human, with cat-like eyes will show as a cat. This may be because the eyes were common in the training data images.

Upload an image of a dog or cat and see if the computer can recognize it.

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.