Hi! I am working on pattern recognition problem of a quasi-periodic signal. Whether ANN or LSTM would be beneficial for this case? It is known that ANN does not have any memorizing concept in its model which basic LSTM have. But, recognition of pattern does actually needs any "memorizing concept" or simple learning through training is enough for this case?
Md Shopon
It depends on what kind of data you are feeding to your neural networks. If your data is in a Sequential Manner in that case you need to use RNN. For example, if you want to make a neural network model that can predict the next word, i.e: A Bird flies in the ........ . For such cases you need to use RNN. However, if your data is not dependant on any previous state then you can use ANN. ,
0 votes
0 thanks
- Badges
- Science topic
- Similar topics
- Organizational Psychology
- Training
More Saikat Chakraborty's questions See All
Similar questions and discussions