Author:
Jérémie Cabessa
Affiliation:
University of Lausanne and University of Massachusetts Amherst, Switzerland
Keyword(s):
Recurrent neural networks, Turing machines, Reactive systems, Evolving systems, Interactive computation, Neural computation, Super-turing.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Cognitive Systems
;
Computational Intelligence
;
Evolutionary Computing
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Reactive AI
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Symbolic Systems
;
Theory and Methods
Abstract:
We consider a model of evolving recurrent neural networks where the synaptic weights can change over time, and we study the computational power of such networks in a basic context of interactive computation. In this framework, we prove that both models of rational- and real-weighted interactive evolving neural networks are computationally equivalent to interactive Turing machines with advice, and hence capable of super-Turing capabilities. These results support the idea that some intrinsic feature of biological intelligence might be beyond the scope of the current state of artificial intelligence, and that the concept of evolution might be strongly involved in the computational capabilities of biological neural networks. It also shows that the computational power of interactive evolving neural networks is by no means influenced by nature of their synaptic weights.