Grand unified theory of AI: Combining top-down with bottom-up

See original at Science Daily

In the 1950s and '60s, artificial-intelligence researchers saw themselves as trying to uncover the rules of thought. But those rules turned out to be way more complicated than anyone had imagined. Since then, artificial-intelligence (AI) research has come to rely, instead, on probabilities -- statistical patterns that computers can learn from large sets of training data.

The most well-known example of the top-down approach to AI is the Cyc project. I wonder how it could be combined with bottom-up approaches?