Stories tagged Harvard

Dec
06
2009

Finding better ways for computers to see

.

Building biologically-inspired vision systems

Living organisms are very good at making sense out of what they see. Designing machines that can recognize objects when seen from an angle or at various distances is challenging. Facial or gesture recognition is becoming common in our computing devices.

Reverse engineering the visual cortex

In an attempt to improve upon current state of the art visual systems, scientists are attempting to reverse engineer biological visual systems.

Huge advances have been recently made in visualizing the structure of our visual cortex (hardware) but the inner workings of the neuronal systems (software) remain a mystery. Mimicking natural selection, scientists are testing thousands of software algorithms at a time.

Using processors from game playing computers

Using graphical processors from game playing computers (such as those found in the PlayStation 3 and high-end NVIDIA graphics cards), scientists have discovered better visual modeling systems.

"The best of these models, drawn from thousands of candidates, outperformed a variety of state-of-the-art vision systems across a range of object and face recognition tasks."

"GPUs are a real game-changer for scientific computing. We made a powerful parallel computing system from cheap, readily available off-the-shelf components, delivering over hundred-fold speed-ups relative to conventional methods,"

Sources
PLoS Computational Biology published research paper
PhysOrg.com
Visual Neuroscience Group @ The Rowland Institute at Harvard

Mar
04
2007

Last fall I attended a talk by one of the other students at my university (Harvard). He was discussing recent results from a perception experiment he had posted online. He said he had over a thousand subjects. "How long have you had this experiment online," I asked him. "Just over a week," he responded.

"Holy crap!" I thought. There are many experiments I would love to do except they require hundreds or thousands of subjects -- something that just isn't feasible in a traditional laboratory setting. So I started the Visual Cognition Online Laboratory. I am getting respectable traffic after one week, but it's going to take a while before I am getting 1,000 participants per week, which is what I need.

Most experiments, I should say, are surveys. What this grad student and I are doing is putting up actual perception experiments, which are always done in the lab. Most researchers believe you need strong controls in timing, display, etc., in order to do perception experiments. For some, this is true, but there are many you can do online given how much bandwidth there is now. Also, if you have enough subjects, that extra noise will wash out.

If you are interested in trying out one of my experiments, they typically take 5 minutes or less.

Mar
03
2005

In January, Harvard President Lawrence Summers created quite a stir when he suggested that one reason why there are fewer women than men working in math and science is that there are inherent differences between male and female brains. (Summer's full speech can be found here.

The comments created quite a controversy. Enter "Summers Harvard women math speech" into Google and you'll get about 28 thousand hits. Many people are reluctant to accept the idea that men and women are inherently different.