September 28, 2008
Helicopters teach themselves to do aerial maneuvers
I just read this article: Helicopters teach themselves to do aerial maneuvers, about the work by my friend Andrew Ng and his grad students at Stanford. This is really impressive.
Stanford computer scientists have developed an artificial intelligence system that enables robotic helicopters to teach themselves to fly difficult stunts by watching other helicopters perform the same maneuvers. The technique is known as “apprenticeship learning.” The result is an autonomous helicopter than can fly dazzling stunts on its own.
September 11, 2008
Marissa Mayer on the Future of Search
The Official Google Blog is running a series in which search experts pontificate on the future of search. In the first installment, Google’s VP of Products, Marissa Mayer, writes about the future of search.
I really liked the article. Here are a few thoughts I had while reading the article.
This past Saturday, I kept track of the things that came up in conversation that I wanted to search for right then but couldn’t:
Are “fab,” “goy” and “eely” words? (There was a Scrabble game going on.) What time does J.C. Penney open on Saturday? Which school has a team called the Banana Slugs? What is the team mascot for San Jose State? How much power does that hydroelectric dam generate? What do you call a group of turkeys? What time does Tropic Thunder show? What’s the name of that great Irish flute player, first name James? What’s the name of the largest city in Russia after Moscow and St. Petersburg? Which is older, a redwood or a cypress? What’s the oldest living thing and how old is it? Who sings “Queen of Hearts”? What kind of bird is that flying over there? Is the “LF” in San Francisco on Union Square or Union Street? What are the dance steps to the Charleston? What day of the week was The Lawrence Welk Show on? What are the lyrics to “In the Mood”? How does Coumadin differ from aspirin in its blood thinning effects? What was the story behind the naming of the number “googol”?
Looking at this list, two things are very clear: (1) I could do a lot more searches and (2) search still has a lot of opportunity for innovation, change, and progress. There are lots of ways that search will need to evolve in order to easily meet user needs. Let’s look at some of my unanswered questions from Saturday and consider how search might change over the next 10 years.
Thinking about the questions one might have asked, but didn’t, is a nice way to recognize some gaps in search. Mayer concludes that she could answer all of her queries with search today, using the right keyword query, but that there must have been easier ways of getting there. It would be really interesting to see how much work it would take ordinary searchers to get these same answers using keyword search, or even how many tries it took Marissa to get the intended results.
The points Marissa makes as follow-ons (including the value of natural language, voice, context, disambiguation, multimedia, and mobility) are all big and important problems.
I also liked her summary of the ideal search engine:
Your best friend with instant access to all the world’s facts and a photographic memory of everything you’ve seen and know. That search engine could tailor answers to you based on your preferences, your existing knowledge and the best available information; it could ask for clarification and present the answers in whatever setting or media worked best.
One interesting aspect of this definition is that it envisions that search engines will still exist as a category in the ideal future. I think there will always be value in having an automated, intelligent conversational partner, and I am a strong proponent of such a future vision. But I also think that increased search intelligence will find its way into the flow of our daily lives and tasks. While there is value in answering factual questions in just the right way, there might be at least as much value in helping us with the task-oriented context in which the questions arise (why do we want movie times, why are we asking about pain killer ingredients) and in helping us to read the content once it is finally returned.
Anyway, I look forward to the rest of the series on the future of search. It’s a good time for this dialogue as I start out in my new role as search strategist and evangelist at Microsoft.
September 3, 2008
Computer Beats Pro at US Go Congress
Slashdot | Computer Beats Pro At US Go Congress
Bob Hearn writes:
“I was in attendance at the US Go Congress match yesterday where history was made: the go program MoGo, running on an 800-core supercomputer, beat 8-dan professional go player Myungwan Kim in a 9-stone handicap game. Most in the audience were shocked at the computer’s performance; it was naturally assumed that the computer would be slaughtered, as usual. Go is often seen as the last bastion of human superiority over computers in the domain of board games. But if Moore’s law continues to hold up, today’s result suggests that the days of human superiority may be numbered.”
I am a Go player, and started my ph.d. research on computer approaches to go in the early 90′s. This is an amazing achievement. Some commentators have downplayed the significance because the Go program received a 9-stone handicap. But what they don’t realize is that a serious amateur Go player (like myself) would not likely be able to beat a professional 8-dan player with that same handicap.
The approach used by these Go programs, which involves simulating millions of random games to the very end and backing up the outcomes to select the best current move, is similar to what my friend Bruce Abramson developed in his PhD work on “Expected Outcome” model of learning and search.
It’s interesting to see these ideas take 20 years to yield fruit.
I think we’re going to see a lot more progress based on AI ideas developed in the 80′s and early 90′s over the next 5 years.
My prediction for when a Go program beats a human professional with no handicap: 2015.