Friday, September 30, 2022

Explainable AI & Quantum

 Much "AI" in use today is basic machine learning, which is frequently simply statistics, which have been in use since the first actuarial and ordnance tables were devised to predict risk or targets...so several hundred years (or longer if the Greeks or Phoencians or Minoans used same math they had for astronomy for landing greek fire on other ships accurately, or insure their ships' cargo against storm damage...


As for autonomy, this occurred as soon as someone built a feedback loop: My fave paper on this james clark maxwell's Royal Society paper 

On Governors back in 1868



For "black box" (as in "inexplicable" AI)- this is true of any system so complex that few or no single human understands all of it - so pretty much any smart phone (without even getting into what goes on in the camera s/w) - nobody could both design the chip and write

the OS (actually i think i know one person, but he's probably the last).



A "deep learning" (aka neural net) is usually explainable if someone just spends the time and energy (it is computationally pricey) - two techniques


1/ shapley values for example here



2/ energy landscapes - as in this

https://www.pnas.org/doi/full/10.1073/pnas.1919995117


Roughly, you can think about comuting significant changes in the entropy of the net at any step in training, and then, using shapley values on input features, identify what caused that change in the neural network (analogous to change point detection, with thresholds etc) and then export the feature list + decision as a new branch in a decision tree or random forest (for example).


So interestingly, once you have built an explanation for a neural net, you can often replace the thing with a random forest or other directly (i.e. self explaining) approach - this was sort of obvious too once people realised you could massively compress neural nets (even using lossy compression algorithms - like video) suggesting most the links and weights were redundant.


So here's the quantum bit (pun intended) - the problem with computing shapley values and energy landscapes at every step in the training iteration is that it is very expensive (compared to the training itself), so if we have to do it often, this is unsustainable.


However, these (especially the energy landscape) might be amenable to computation by an analog quantum computer (described herein ) perhaps making this affordable. Analog quantum computers are available, indeed have been applied to expensive problems like the transfer function of a 3D space to multiple radios - see princeton work on this).