Connectionists: Predicting Action Content On-Line and in Real Time before Action Onset — an Intracranial Human Study

[Uri Maoz]

Hello Colleagues,

My apologies for any cross postings.
I would like to draw your attention to a recent publication at NIPS. It can be found at:

http://nips.cc/Conferences/2012/Program/event.php?ID=3432 (the link to the full paper is at the very bottom of the page). 

Maoz U, Ye S, Ross I, Mamelak A and Koch C (2012) Predicting Action Content On-Line and in Real Time before Action Onset – an Intracranial Human Study. Advances in Neural Information Processing Systems 25, MIT Press 

Abstract
The ability to predict action content from neural signals in real time before action onset has been long sought in the neuroscientific study of decision-making, agency and volition. On-line real-time (ORT) prediction is important for understanding the relation between neural correlates of decision-making and conscious, voluntary action. Here, epilepsy patients, implanted with intracranial depth microelectrodes or subdural grid electrodes for clinical purposes, participated in a “matching-pennies” game against either the experimenter or a computer. In each trial, subjects were given a 5s countdown, after which they had to raise their left or right hand immediately as the “go” signal appeared on a computer screen. They won a fixed amount of money if they raised a different hand than their opponent and lost that amount otherwise. The working hypothesis of this experiment was that neural precursors of the subjects’ decisions precede action onset and potentially also the awareness of the decision to move, and that these signals could be detected in intracranial local field potentials (LFP). We found that low-frequency LFP signals from a combination of 10 channels, especially bilateral anterior cingulate cortex and supplementary motor area, were predictive of the intended left-/right-hand movements before the onset of the go signal. Our ORT system predicted which hand the patient would raise 0.5s before the go signal with 68±3% accuracy in two patients. Based on these results, we constructed an ORT system that tracked up to 30 channels simultaneously, and tested it on retrospective data from 6 patients. On average, we could predict the correct hand choice in 80% of the trials, which rose to 90% correct if we let the system drop about 1/3 of the trials on which it was less confident. Our system demonstrates – for the first time – the feasibility of accurately predicting a binary action in real time for patients with intracranial recordings, well before the action occurs.

Uri Maoz
Postdoctoral Scholar
Division of Biology, MC 216-76
California Institute of Technology
Pasadena, CA 91125
Tel: (626) 395-8961
Email: urim at caltech.edu 
www.klab.caltech.edu/~urim
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20130411/00437fac/attachment.html>