-
-
Notifications
You must be signed in to change notification settings - Fork 79
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Regression with Norse #254
Comments
Yes, it is possible to implement regression tasks, this is mostly down to the choice of Loss function. One thing that is tricky and an active area of research is how to best define a loss which only operates on spike times in order to do fit for example the behaviour of a Neuron model to measurements. I can look into adding an example in the documentation. |
One way could be to add a linear output layer, which converts a (sufficiently large) number of spikes to numeric values. This wouldn't be "pure", but it should work with standard losses. But I am curious to see other approaches. Looking forward to the examples, maybe with hints to publications? |
I have some example code lying around that does regression on sum of sines, which I could add. |
Is there a way to perform regression tasks with Norse? If so can you kindly provide an example notebook or a link from the documentation.
The text was updated successfully, but these errors were encountered: