USING GPU’S TO DECIPHER ANIMAL (AND HUMAN) CROWD BEHAVIOR

by Tony Kontzer

You’d be hard-pressed to find an example of technology with the potential to change the course of humanity more than the one provided by behavioral ecologist Iain Couzin at Wednesday’s GTC keynote address.

Couzin, a postdoctoral research fellow at Princeton’s Department of Ecology and Evolutionary Biology, is conducting research that could help humans not only grasp the mysteries of collective animal behavior, but potentially apply that understanding to our own tendencies.

Thousands of attendees packed the keynote hall
for Prof. Couzin’s presentation

Couzin focuses on how and why animals collectively behave the way they do. And he credits CUDA with enabling him to simulate group behavior in ways that were previously impossible.

“The whole way I do science has been transformed by GPU computing,” Couzin told the audience of some 2,500 attendees. “We can spend $500 [for a GPU] and suddenly have more computational power than we could have dreamed of the previous year.”

Not that he’s settling for such an off-the-shelf approach; Couzin is so jazzed by the impact of GPUs on his work that he said he’s working on getting funding to establish a larger, more established GPU-based system. He has his sights set on upgrading the four PCs packed with GeForce and Tesla boards currently used in his lab.

Those little colored dots on the screen represent
a school of simulated fish

One way he’s using GPUs in his research is to simulate the movements of schooling fish – up to 32,000 of them. The GPUs allow him to simulate the impact of certain stimuli on collective behavior. “As a biologist, I want to get inside the heads of these individuals and understand how they communicate and coordinate,” he said.

To illustrate, he provided compelling examples of how he’s accomplishing this. These include:

  • Applying mathematical equations to understand why fish, when stimulated, naturally form a swirl around an empty center.
  • Modeling the behavior of fish in at-risk environments, such as the Gulf of Mexico, to determine how a deleterious event, like the BP oil spill, can impact group decision-making.
  • Using robotic predators to study responses to attacks, with the goal of determining  strategies for how to best stimulate, counter or otherwise contend with group behavior.
  • Studying the impact of how uninformed individuals affect group decision making.

In this last example, he made a startling discovery. Counter to the conventional wisdom that uninformed humans are more easily influenced by extremists, his findings suggest that the presence of those without strong views increases the odds that a group will go with the majority opinion.

Watch a replay of this GTC 2012 keynote here.