Bidirectional Recurrent Networks
One disadvantage of recurrent networks is that the state at a particular time unit only has knowledge about the past inputs up to a certain point in a sentence, but it has no knowledge about future states. In certain applications like language modeling, the results are vastly improved with knowledge about both past and future states. A specific example is handwriting recognition in which there is a clear advantage in using knowledge about both the past and future symbols, because it provides a better idea of the underlying context. In the bidirectional recurrent network, we have separate hidden states $\bar{h}_t^{(f)}$ and $\bar{h}_t^{(b)}$ for the forward and backward directions. The forward hidden states interact only with each other and the same is true for the backward hidden states. The main difference is that the forward states interact in the forwards direction, while the backwards states interact in the backwards direction. Both $\bar{h}_t^{(f)}$ and $\bar{h}_t^{(b)}$