O'Reilly logo

Deep Learning with TensorFlow by Ahmed Menshawy, Md. Rezaul Karim, Giancarlo Zaccone

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Bidirectional RNNs

Bidirectional RNNs are based on the idea that the output at time t may depend on previous and future elements in the sequence. To realize this, the output of two RNN must be mixed--one executes the process in a direction and the second runs the process in the opposite direction.

The network splits neurons of a regular RNN into two directions, one for positive time direction (forward states), and another for negative time direction (backward states). By this structure, the output layer can get information from past and future states.

The unrolled architecture of B-RNN is depicted in the following figure:

Unrolled bidirectional ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required