How IBM Watson Learns
Most of us know IBM's Watson computing system from its breakout performance on Jeopardy! a few years back; I covered that earlier today.
But Watson is significant not because it can win at Jeopardy! -- it's significant because it embodies a fundamental shift in how humans interact with computer systems. The new model is that we ask questions, Watson makes connections based on its ability to understand human language, and then it suggests possible answers...along with showing its work.
The fact that we can see the work behind Watson's answers is critically important -- that's not something you get from a simpler system like a search engine. Most interesting is that, because a human selects from among the best answers, humans can teach Watson in a positive feedback loop. Watson can even ask clarifying questions, allowing it to learn yet more about the world, and improving future performance. Watson works in tandem with humans, and sometimes the top answer is not the most useful to us -- it's the second, third, or fourth answer that may hold the key for a rare medical diagnosis, or an obscure connection. By deploying Watson in health care, IBM is helping doctors explore and improve medical care. Let's take a peek inside the IBM Watson Solutions Lab:
IBM calls Watson a "Learning System," and suggests it's the way we will interact with big data in the future. It's an intriguing notion, and it feels right to me. Especially when we talk about applications like health care, the ability for a human to help teach the computer is crucial. Got three and a half minutes to dig into how Watson learns? Watch this video.
If that piqued your interest, here's Manoj Saxena in a longer TEDx talk adding more context, including the tidbit that IBM is training Watson thoroughly enough that it's "within striking distance" of passing the U.S. Medical Licensing Exam (!):
I'll be digging deeper into Watson later today -- stay tuned for more Watson goodness.