Researchers SOMEHOW peered into a black-box AI made for identifying molecules on exoplanets
We can now safely say AI can reliably spot molecules on planets beyond the solar system
Peeking inside the black box
In science, a theory or a tool cannot be adopted if it is not understood. After all, you don’t want to go through the excitement of discovering life on an exoplanet, just to realize it is simply a “glitch” in the AI. The bad news is that AIs are terrible at explaining their own findings. Even AI experts have a hard time identifying what causes the network to provide a given explanation. This disadvantage has often prevented the adoption of AI techniques in astronomy and other scientific fields.
We developed a method that allows us a glimpse into the decision-making process of AI. The approach is quite intuitive. Suppose an AI has to confirm whether an image contains a cat. It would presumably do this by spotting certain characteristics, such as fur or face shape. To understand which characteristics it is referencing, and in what order, we could blur parts of the cat’s image and see if it still spots that it is a cat.
This is exactly what we did for an exoplanet-probing AI by “perturbing”, or changing, regions of the spectrum. By observing how the AI’s predictions on the abundances of exoplanet molecules changed (say water in the atmosphere) when each region was doctored, we started to build a “picture” of how the AI thought, such as which regions of the spectrum it used for deciding the level of water in the atmosphere.
Reassuringly for us astronomers, we found that a well-trained AI relies heavily on physical phenomena, such as unique spectroscopic fingerprints – just like an astronomer would. This may come as no surprise, after all, where else can the AI learn it from?
In fact, when it comes to learning, AI is not so different from a cheeky high-school student – it will try its best to avoid the hard way (such as understanding difficult mathematical concepts) and find any shortcuts (such as memorizing the mathematical formulae without understanding why) in order to get the correct answer.
If the AI made predictions based on memorizing every single spectrum it had come across, that would deeply undesirable. We want the AI to derive its answer from the data, and perform well on unknown data, not just the training data for which there is a correct answer.
This finding provided the first method to have a sneaky peek into so-called “AI black-boxes”, allowing us to evaluate what the AIs have learnt. With these tools, researchers now can not only use AIs to speed up their analysis of exo-atmospheres, but they can also verify that their AI uses well-understood laws of nature.
That said, it’s too early to claim that we fully understand AIs. The next step is to work out precisely how important each concept is, and how it gets processed into decisions.
The prospect is exciting for AI experts, but even more so for us scientists. AI’s incredible learning power originates from its ability to learn a “representation”, or pattern, from the data – a technique similar to how physicists have discovered laws of nature in order to better understand our world. Having access to the minds of AI may therefore grant us the opportunity to learn new, undiscovered laws of physics.
This article byKai Hou (Gordon) Yip, Postdoctoral Research Fellow at ExoAI,UCLandQuentin Changeat, Postdoctoral Research Fellow in Astronomy,UCL, is republished fromThe Conversationunder a Creative Commons license. Read theoriginal article.
Story byThe Conversation
An independent news and commentary website produced by academics and journalists.An independent news and commentary website produced by academics and journalists.
Get the TNW newsletter
Get the most important tech news in your inbox each week.
