search

KindXiaoming / pykan

Kolmogorov Arnold Networks
MIT License
14.49k stars 1.33k forks source link

Quick question: why should you pass in the input in order to plot the network? #409

Open jink1994 opened 4 weeks ago

jink1994 commented 4 weeks ago

As in the title.

I want to optimize the code a bit but not sure if there are other reasons for which the authors do it like this. After all, when the training is done, shouldn't you be able to visualize the network based on parameters directly?

Looking forward to your thought, thanks!

KindXiaoming commented 3 weeks ago

To visualize internal 1D functions, we need intermediate activations, which are defined on inputs. If a 1D function is sin(x) globally, but inputs are all close to zero, the visualization will need to reveal that this is nearly a linear function for the range of interest. It appears more like a feature to me, but one may be able to find a way to get rid of the need to pass inputs.

stupidnubnubnub commented 3 weeks ago

@KindXiaoming I'm wondering whether the symbolic representation of 1D function where input is passed and one of function where input is NOT passed is different of not, can I ask your opinion?

jink1994 commented 3 weeks ago

Thanks for the quick response, Xiaoming! To

@KindXiaoming I'm wondering whether the symbolic representation of 1D function where input is passed and one of function where input is NOT passed is different of not, can I ask your opinion?

I can answer this:

No they are not. Like what XIaoming said above, given a different range of interests, the 1D function can be very different in visualizations. This is partially due to that splines enables local updates, which means that the symbolic representation for a local domain can be different globally.