Needless to say, the title of this story is a little misleading, in that we aren’t dealing with artificial-intelligence, and thus, the possibility of robots reading our thoughts and acting accordingly to kill us all is remote. However, for the study of our brain and the possible resolution to disorders such as autism and paranoid schizophrenia, new research from a pair at Carnegie Mellon University has taken a great step forward.
Tom Mitchell, a computer scientist, and Marcel Just, a cognitive neuroscientist, both of Carnegie Mellon University, have published a research paper today in the latest edition of the journal
Science. Their findings demonstrate how our understanding of how the brain processes thoughts and information is being increased thanks to computational modeling.
Mitchell and Just have gained previous recognition for their work, supported by the National Science Foundation (NSF) and the W.M. Keck Foundation, using functional magnetic resonance imaging (fMRI) to detect and locate brain activity when someone thinks about a certain word.
With that information behind them, the Carnegie Mellon pair moved on to use that information to build a computational model that enabled a computer to correctly determine what word a research subject was thinking about, simply by analyzing brain scan data.
Their next step was to make an even more advanced model that would allow a computer to predict the brain activation patterns associated with concrete nouns, or those things that we experience through our sense. This model allowed the computer to determine the word, even if the computer did not have the fMRI data for that specific noun.
"We believe we have identified a number of the basic building blocks that the brain uses to represent meaning," said Mitchell. "Coupled with computational methods that capture the meaning of a word by how it is used in text files, these building blocks can be assembled to predict neural activation patterns for any concrete noun. And we have found that these predictions are quite accurate for words where fMRI data is available to test them."
Additionally, Just believes that the computational model provides an insight in to the very nature of human thought. "We are fundamentally perceivers and actors," he said. "So the brain represents the meaning of a concrete noun in areas of the brain associated with how people sense it or manipulate it. The meaning of an apple, for instance, is represented in brain areas responsible for tasting, for smelling, for chewing. An apple is what you do with it. Our work is a small but important step in breaking the brain's code."
This work can hopefully lead to the use of brain scans in the identification of thoughts, which could then have applications in the study of autism, thought disorders such as paranoid schizophrenia, and semantic dementias such as Pick’s disease.
"This has been an interesting project to watch," said Kenneth Whang, an official at the NSF, who is responsible for the pairs grant. "They started with some fundamental ideas from machine learning about how to get the most out of fMRI data, and now they've not only shown the power of their computational approach, but also made headway on one of the most important problems in the understanding of language in the brain."
[url=http://www.eurekalert.org/pub_releases/2008-06/nsf-act060208.php]http://www.eurekalert.org/pub_releases/2008-06/nsf-act060208.php[/url]
Joshua Hill, a Geek’s-Geek from Melbourne, Australia, Josh is an aspiring author with dreams of publishing his epic fantasy, currently in the works, sometime in the next 5 years. A techie, nerd, sci-fi nut and bookworm.
