Exploring Temporal Memory of LSTM and Spiking Circuits

We have investigated two specific network types in the class of dynamic neural networks: LSTM and spiking neural networks. Dynamic neural networks in general are computationally powerful and very promising for tasks in which temporal information has to be processed. We’d like to remark that this is the case for virtually any task or application interacting with the real world. We have tested the networks on a broad set of dynamic tasks and most problems were solved by both; there are some fields though where either LSTM or the spiking neural networks performed better. These differences can be largely brought back to the differences between second and third generation networks.