Many scientific problems hinge on finding interpretable formulas that fit data, but neural networks are the outright opposite! Check out our recent work that make neural networks modular and interpretable. If you have interesting datasets at hand, we're happy to collaborate!

paper: code:

Symbolic regression (finding symbolic formulas from data) has been quite successful on some examples, but it also fail completely for others. Instead, our goal is structure regression (finding modular structures from data), which can provide visible insights for all cases.

Interesting work! Is this doable for graph nets? The task would be to locate significant attributed substructures. (I guess such location might be useful to help predesign the library of GSN @mmbronstein )

👀

Great work Ziming! Could you explain Figure 14? I was a bit confused by it.

We suffer in the seizure forecasting field making interpretable models because the features extracted from neural time series are highly correlated. Any tool to understand why our models work would give important insights as to how the brain changes in the lead up to a seizure.

I see some resemblance with Group method of data handling (GMDH) .

👍👍👋 nice！

it's a clever idea, great job!

Can you explain what we are seeing here? Here is my confusion: if you regularize enough, you should see only one layer (either last layer or first layer) activation, the rest is just passing through! Why? Since 1 layer is enough to represent output.