Infusing Intent and Its Management into Turing Machine: A Path to Cognitive Distributed Computing

Abstract

The holy grail of Artificial Intelligence (AI) has been the reproduction of the cognitive processes in Silicon based computing machines to mimic the human or animal cognitive behavior. Computationalism attempts to explain cognition in terms of different internal representations and symbol-manipulating processes operating over these representations. On the other hand, Connectionism explains cognition in terms of a finite automaton which computes associative function specified by a set of input-output pairs that in turn, introduce interaction into the computing model.  However, both theories have critics who believe that they fall short in explaining the cognitive processes observed either in humans or animals. Computationalism tied to the Turing computing model which is restricted to single, sequential processes does not support concurrency, mobility and synchronization observed in cognitive processes. The connectionist systems are also dedicated to single tasks and do not support complex environments which require behaviors that are coordinated and integrated. Above all, cognition is associated with intent of a system and its accomplishment efficiently through various processes that monitor and control itself and its environment. Any computing model incorporating cognition must accommodate dynamic coupling between various elements of the system, where each change in one element continually influences every other element’s direction of change. We discuss the newly introduced DIME (distributed intelligent managed element) computing model which is shown to be one of the implementing architectures for π–calculus and argue that its non-von Neumann parallel implementation of a managed Turing machine with a signaling network overlay addresses some of the limitations of both Computationalism and Connectionism. The DIME network architecture provides a mechanism for injecting sensors and actuators into a Turing Machine and allows implementing autonomic distributed computing where the computers and the programs they execute are orchestrated to achieve the overall intent while optimizing the computing resources available.