Comment by nialse
15 hours ago
Dynamical neurons are not used because they add enormous computational cost and instability for limited practical gain.
15 hours ago
Dynamical neurons are not used because they add enormous computational cost and instability for limited practical gain.
What do you mean by "they add instability"?
Neural nets are unstable during training and dynamic weights amplifies the problem. Thus, the neural networks could end up in totally unusable states at inference time.