Supervised vs Unsupervised learning

The core idea behind supervised learning is feature extraction from the ideal (pattern/model), and then training the neural network to identify these features in the training data.

On the other hand, Unsupervised learning is based not on features but on edges. The core idea is to use the ideal item to detect edges and then detect the same (sequence/pattern of ) edges in the real input to identify the item.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s