GRU vs LSTM - Explain the difference.
The key difference between a GRU and an LSTM is that a GRU has two gates (reset and update gates) whereas an LSTM has three gates (namely input, output and forget gates).
Why do we make use of GRU when we clearly have more control on the network through the LSTM model (as we have three gates)? In which scenario GRU is preferred over LSTM?
GRU vs LSTM
GRUs and LSTMs utilize different approaches toward gating information to prevent the vanishing gradient problem. Here are the main points comparing the two: The GRU unit controls the flow of information like the LSTM unit, but without having to use a memory unit. It just exposes the full hidden content without any control. GRUs are relatively new, and in my experience, their performance is on par with LSTMs, but computationally more efficient (as pointed out, they have a less complex structure). For that reason, we are seeing it being used more and more. For a detailed description, you can explore this research paper on Arxiv. The paper explains all this brilliantly. You can also explore these blogs for a better idea: WildML
Colah - Github