What is Deep learning?

Definition

Deep learning also called as deep structured learning or hierarchical learning. Deep learning is part of machine learning techniques based on artificial neural networks.

The word “deep” means the number of layers through which the data is reconstructed.

The deep learning process goes level vise.

Deep learning level learns to reconstruct its input into a more involved and composite structure.

Deep learning uses various layers to progressively obtain higher-level features from unprocessed input.

For example: An image recognition application, the input can be pixels pattern

  1. The first layer may separate the pixels and encode frames.
  2. The second layer form and encode organizations of frames.
  3. The third layer encodes a nose and eyes.
  4. The fourth layer acknowledges that the image holds a face.

The types of deep learning

  1. Supervised
  2. Semi-supervised
  3. Unsupervised

Deep learning employs in below fields

  • Computer vision
  • Speech recognition
  • Natural language processing
  • Audio recognition
  • Social network filtering
  • Machine translation
  • Bioinformatics
  • Drug design
  • Medical image analysis
  • Material inspection
  • Board game programs

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 )

Google photo

You are commenting using your Google 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 )

Connecting to %s

%d bloggers like this: