Difference b/w CNNs and RNNs

  • CNNs
    • With CNNs, all we’re doing is training our neural net to identifying/labelling the input in the same or some other form, but literally. For instance:
      • Text recognition is basically taking in an image of text and labelling it as “some text”
      • Image recognition is again simply taking in an image of an object and labelling it as an object say “car”
  • RNNs
    • With RNNs, our goal is to simply convert the input into a “Thought Vector”, which represents the input.
    • Once this is done, this “Thought Vector” can be represented as any literal output like Text or Speech or Image.

 

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