Open Dignity-ghost opened 2 years ago
Hi, I use ArcTan: https://spikingjelly.readthedocs.io/zh_CN/latest/spikingjelly.clock_driven.surrogate.html#atan-init-en
Thanks for replying. May I ask did you test ATan is more efficient than Sigmoid?
Does efficient
mean higher accuracy? In my early experiments, ArcTan does have higher accuracy than Sigmoid. But it may depend on network structure. So, I suggest you can test different surrogates in https://spikingjelly.readthedocs.io/zh_CN/latest/spikingjelly.clock_driven.surrogate.html .
Does
efficient
mean higher accuracy? In my early experiments, ArcTan does have higher accuracy than Sigmoid. But it may depend on network structure. So, I suggest you can test different surrogates in https://spikingjelly.readthedocs.io/zh_CN/latest/spikingjelly.clock_driven.surrogate.html .
Yes, I got it. Thank you very much.
Dear author, what kind of grad function do you used in SEW cext_neuron.MultiStepIFNode? Sigmoid?