New Explainable AI Algorithms

That's a very good question.

You're right that the way we typically train Tree Ensembles creates a massive number of rules, the walk through Random Forest has more than 100,000 leaves per Decision Tree. Once we start grafting it the number of rules starts to vastly outnumber the amount of training data.

I have some follow up articles planned that will cover this in more detail, but the short answer is that I feel that we often jump to overly complex models up front without fully considering whether the accuracy/complexity tradeoff it worth it. Using Amalgamate I showed how I could have the number of rules without significantly increasing validation error (+5%). I believe that if we're careful using model sophisticated techniques (i.e. Boosting and dense/fully connected/tabular neural networks) then we should be able to create reasonably accurate models that are reasonably straight forward to explain.

This is really nice work.

If you had a mechanism to subscribe for future updates, I'd do it.

Either way, this is cool stuff.

I took Show HN out of the title because this seems more like reading material (https://news.ycombinator.com/showhn.html). It's very good though, so I also put it in the second-chance pool (https://news.ycombinator.com/item?id=11662380).

(While I have you, would you mind adding an email address to your profile that we can contact you at? We do that sometimes when we want to invite a repost.)

Thanks :)

Yep, code's on GitHub. I'm more than happy to collaborate, there's heaps of things that need to be done.

That works to a point, but it doesn't necessarily find all the rules of the model. In the post I walked through a model with three training records (yellow, blue, red) which created six prediction boundaries. Half of the rules weren't covered by the training data, which makes them hard to find without an efficient algorithm to search out all possible rules. The risk of undiscovered rules is they may cause unexpected behaviour that leads to bad predictions - and if you haven't described the whole model then it will be impossible to know how many of these potentially bad predictions exist.

Do you have any references/explainers for that approach? Would be interested to read!