Back to the future: The return of cognitive functionalism.

Journal: The Behavioral and brain sciences
Published Date:

Abstract

The claims that learning systems must build causal models and provide explanations of their inferences are not new, and advocate a cognitive functionalism for artificial intelligence. This view conflates the relationships between implicit and explicit knowledge representation. We present recent evidence that neural networks do engage in model building, which is implicit, and cannot be dissociated from the learning process.

Authors

  • Leyla Roskan Çağlar
    Psychology Department,Rutgers University Brain Imaging Center (RUBIC),Rutgers University,Newark,NJ 07102.lcaglar@psychology.rutgers.edujose@rubic.rutgers.eduhttps://leylaroksancaglar.github.io/http://nwkpsych.rutgers.edu/~jose/.
  • Stephen José Hanson
    Psychology Department,Rutgers University Brain Imaging Center (RUBIC),Rutgers University,Newark,NJ 07102.lcaglar@psychology.rutgers.edujose@rubic.rutgers.eduhttps://leylaroksancaglar.github.io/http://nwkpsych.rutgers.edu/~jose/.