# Need Help With LSTM Neural Networks

I have been researching LSTM neural networks. I have seen this diagram a lot and I have few questions about it. Firstly, is this diagram used for most LSTM neural networks?

Secondly, if it is, wouldn't only having single layers reduce it's usefulness?

(2) It is very common for researchers to use more than one layers of LSTM and achieves better performance than a single layer one. A common way to "stack" LSTMs is to use the previous layer's output ($h_t$ in your diagram) as the input to the next layer ($x_t$). However, I have seldom seen any successful application of 5+ layers of LSTMs, while for CNNs it is common to use tens or even hundreds of layers.