Is the input in Recurrent Connection and Spiking LSTM examples real value? #241
Unanswered
Yang-J-LIN
asked this question in
Q&A
Replies: 1 comment
-
The user is free to input spikes or float values. To get spikes, the user can use the encoder.
It depends on how the user design and train the SNN. Refer to #182 . |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I am trying to use SNN for sequential data so I have a look at examples of recurrent connection and spiking LSTM. However, it seems that the input to the SNN is real value instead of spike trains. Is that correct? If so, how does it perform if the input is changed to latency or rate-based coding input?
Beta Was this translation helpful? Give feedback.
All reactions