Mind-Reading Machine Could Someday Replace Keyboard

Mind-reading devices could make carpal tunnel a thing of the past by eliminating the need for a keyboard.

According to the Princeton University release (via Innovation News Daily), functional magnetic resonance imaging (fMRI) scans show activity in the brain associated with certain words:

“The long-term goal is to translate that brain-activity pattern into the words that likely describe the original mental ‘subject matter,'” Matthew Botvinick, a psychologist at Princeton University’s Neuroscience Institute, said. “One can imagine doing this with any mental content that can be verbalized, not only about objects, but also about people, actions and abstract concepts and relationships. This study is a first step toward that more general goal.

“If we give way to unbridled speculation, one can imagine years from now being able to ‘translate’ brain activity into written output for people who are unable to communicate otherwise, which is an exciting thing to consider. In the short term, our technique could be used to learn more about the way that concepts are represented at the neural level — how ideas relate to one another and how they are engaged or activated.”

An MRI machine can takes brain scans, which researchers are using to track activity associated with certain thoughts (Image Editor/Flickr via Live Science)

Technology like this is still years in the making, and if and when it’s available, it will first be used to help people who are completely paralyzed. Innovation News Daily reports that current technology to help those who cannot communicate due to paralysis includes that which allows the patient to select letters with their eyes to form words and a prototype that uses synthesized voices to create sound from thoughts, though not yet actual words.

The Princeton researchers, delving further into technology of creating words from thoughts, found that fMRI brain scans showed patters when thinking about objects such as horse or house. The scans were also used to identify words that were related to topics:

. . . thinking about “eye” or “foot” showed patterns similar to those of other words related to body parts.

While brain scans can in a relatively easy manner, track brain activity that is associated with images, thoughts and words associated with those images and subjects can be more difficult:

“Someone will start thinking of a chair and their mind wanders to the chair of a corporation then to Chairman Mao — you’d be surprised,” said Francisco Pereira, lead author of the study. “The brain tends to drift, with multiple processes taking place at the same time. If a person thinks about a table, then a lot of related words will come to mind, too. And we thought that if we want to understand what is in a person’s mind when they think about anything concrete, we can follow those words.”

Building off of already established research of brain scans taken from volunteers looking at images and words, Pereira and his colleagues collected topics from thousands of Wikipedia articles using a computer program developed by Princeton professor. Objects in the articles ranged from airplanes to heroin to birds to manual transmission. Related topics to these objects were then generated. Researchers looked at the brain scans to find similar activity for a certain topic to establish common brain patters for a whole subject. They produced color-coded figures that illustrate the probability of words within the Wikipedia article about the object the participant saw during the scan actually being associated with the object.

The more red a word is, the more likely a person is to associate it, in this case, with "cow." On the other hand, bright blue suggests a strong correlation with "carrot." Black and grey "neutral" words had no specific association or were not considered at all. (Illustration courtesy of Francisco Pereira)

[H/T Live Science]