Introduction to AI and Predictions
Back in the 17th century, German astronomer Johannes Kepler figured out the laws of motion that made it possible to accurately predict where our solar system’s planets would appear in the sky as they orbit the sun. But it wasn’t until decades later, when Isaac Newton formulated the universal laws of gravitation, that the underlying principles were understood. Although they were inspired by Kepler’s laws, they went much further, and made it possible to apply the same formulas to everything from the trajectory of a cannon ball to the way the moon’s pull controls the tides on Earth — or how to launch a satellite from Earth to the surface of the moon or planets.
The Current State of AI
Today’s sophisticated artificial intelligence systems have gotten very good at making the kind of specific predictions that resemble Kepler’s orbit predictions. But do they know why these predictions work, with the kind of deep understanding that comes from basic principles like Newton’s laws? As the world grows ever-more dependent on these kinds of AI systems, researchers are struggling to try to measure just how they do what they do, and how deep their understanding of the real world actually is.
Assessing AI’s Understanding
Now, researchers in MIT’s Laboratory for Information and Decision Systems (LIDS) and at Harvard University have devised a new approach to assessing how deeply these predictive systems understand their subject matter, and whether they can apply knowledge from one domain to a slightly different one. And by and large the answer at this point, in the examples they studied, is — not so much. The findings were presented at the International Conference on Machine Learning, in Vancouver, British Columbia, last month by Harvard postdoc Keyon Vafa, MIT graduate student in electrical engineering and computer science and LIDS affiliate Peter G. Chang, MIT assistant professor and LIDS principal investigator Ashesh Rambachan, and MIT professor, LIDS principal investigator, and senior author Sendhil Mullainathan.
Understanding vs. Prediction
“Humans all the time have been able to make this transition from good predictions to world models,” says Vafa, the study’s lead author. So the question their team was addressing was, “have foundation models — has AI — been able to make that leap from predictions to world models? And we’re not asking are they capable, or can they, or will they. It’s just, have they done it so far?” “We know how to test whether an algorithm predicts well. But what we need is a way to test for whether it has understood well,” says Mullainathan, the Peter de Florez Professor with dual appointments in the MIT departments of Economics and Electrical Engineering and Computer Science and the senior author on the study.
Testing AI’s Understanding
In the Kepler versus Newton analogy, Vafa says, “they both had models that worked really well on one task, and that worked essentially the same way on that task. What Newton offered was ideas that were able to generalize to new tasks.” That capability, when applied to the predictions made by various AI systems, would entail having it develop a world model so it can “transcend the task that you’re working on and be able to generalize to new kinds of problems and paradigms.” The team developed a new metric, a way of measuring quantitatively how well a system approximates real-world conditions. They call the measurement inductive bias — that is, a tendency or bias toward responses that reflect reality, based on inferences developed from looking at vast amounts of data on specific cases.
Examples and Results
The team looked at different examples of predictive AI systems, at different levels of complexity. On the very simplest of examples, the systems succeeded in creating a realistic model of the simulated system, but as the examples got more complex that ability faded fast. For example, in a two-state or three-state lattice, we showed that the model does have a pretty good inductive bias toward the actual state,” says Chang. “But as we increase the number of states, then it starts to have a divergence from real-world models.” A more complex problem is a system that can play the board game Othello, which involves players alternately placing black or white disks on a grid. The AI models can accurately predict what moves are allowable at a given point, but it turns out they do badly at inferring what the overall arrangement of pieces on the board is, including ones that are currently blocked from play.
Conclusion
People are already trying to use these kinds of predictive AI systems to aid in scientific discovery, including such things as properties of chemical compounds that have never actually been created, or of potential pharmaceutical compounds, or for predicting the folding behavior and properties of unknown protein molecules. “For the more realistic problems,” Vafa says, “even for something like basic mechanics, we found that there seems to be a long way to go.” This work shows there’s a long way to go, but it also helps to show a path forward. “Our paper suggests that we can apply our metrics to evaluate how much the representation is learning, so that we can come up with better ways of training foundation models, or at least evaluate the models that we’re training currently,” Chang says.
FAQs
Q: What is the main difference between Kepler’s laws and Newton’s laws?
A: Kepler’s laws describe the motion of planets, while Newton’s laws provide a deeper understanding of the underlying principles of gravity and motion.
Q: Can AI systems currently make predictions as accurate as Newton’s laws?
A: No, while AI systems can make accurate predictions in specific tasks, they lack the deep understanding of the underlying principles that Newton’s laws provide.
Q: What is inductive bias, and how is it used to measure AI’s understanding?
A: Inductive bias is a measure of how well an AI system’s predictions reflect reality, based on inferences developed from looking at vast amounts of data on specific cases.
Q: What are the implications of this research for the development of AI systems?
A: This research highlights the need for AI systems to develop a deeper understanding of the world, rather than just making accurate predictions, and provides a metric for evaluating their understanding.
