Saturday, March 29, 2008

To Bloom or Not to Bloom

At dawn, I left Washington D.C. after going by the tidal basin of the Potomac where the cherry blossoms were in full bloom around the Jefferson Memorial. In "Now Blooming: Digital Models," The Washington Post describes how chief horticulturalist Rob DeFeo of the National Park Service, which maintains a page on the cherry blossoms, tries to predict when the height of the season will be by examining the blossoms and using his judgment about the annual cycle of the tree in response to its environment. In contrast two graduate students, Vidhya Dass and Elizabeth Brennan have developed a computer program that will forecast the cherry blossom apex based on "artificial neural networks, evolutionary computations, the Arrhenius equation, linear regression and something called fuzzy logic."

Dass and Brennan said they focused on computational intelligence and essentially tried to mimic the working of the human brain. This involved considering such things as "multiple-layered feed forward neural networks," they wrote in their paper, as well as "delta rule," "topology" and "Stochastic gradient method."

A neural network model, by the way, "is like the brain," Dass said. "You know how our human brain absorbs complex relationships? It's something very similar to that. You would train a neural network . . . like the brain, and then after a while, it would be able to . . . predict the actual phenomenon."

Fuzzy logic is another malleable brainlike data processing system that adjusts itself as it gets feedback, Dass said. And the famous equation of Swedish chemist Svante August Arrhenius calculates the speed of a chemical reaction based on temperature.

The trees were a gift from Japan in 1912 from the mayor of Tokyo, a city that the students point out uses these high-tech methods to anticipate its own "sakura" season in the region. Unfortunately, the Post's coverage did little to demystify the work of information scientists working on real-world problems, even as it attempted to define common phrases in the discipline's terminology, because much of the students' work had to do with common sense factors like weather.

Labels: , , , ,


Post a Comment

<< Home