Reputation: 11
Hope you are doing well,
I am doing a research paper about wind energy forecasting using deep learning. Where I used 3 neural networks namely: RNN, LSTM, MLP. The results were good, but the thing that I found somewhat strange is the superiority of MLP over LSTM, where GRU achieved the best value than MLP and finally LSTM. It is known that LSTM is often the one that achieves the best values in the time series forecasting. Note that the differences are not very large. Can this be considered logical, especially in a research paper? Another question: if a one type of ANN for example GRU performs better than LSTM in one metric and not in another, how can we explain that ?
Thanks
Upvotes: 1
Views: 392