Analog computation via neural networks
Theoretical Computer Science
On the computational power of neural nets
Journal of Computer and System Sciences
The dynamic universality of sigmoidal neural networks
Information and Computation
Why interaction is more powerful than algorithms
Communications of the ACM
Interactive foundations of computing
Theoretical Computer Science - Special issue: theoretical aspects of coordination languages
Neural networks and analog computation: beyond the Turing limit
Neural networks and analog computation: beyond the Turing limit
Persistent Turing Machines as a Model of Interactive Computation
FoIKS '00 Proceedings of the First International Symposium on Foundations of Information and Knowledge Systems
Beyond the Turing Limit: Evolving Interactive Systems
SOFSEM '01 Proceedings of the 28th Conference on Current Trends in Theory and Practice of Informatics Piestany: Theory and Practice of Informatics
Computation: finite and infinite machines
Computation: finite and infinite machines
Interactive Computation: The New Paradigm
Interactive Computation: The New Paradigm
How We Think of Computing Today
CiE '08 Proceedings of the 4th conference on Computability in Europe: Logic and Theory of Algorithms
Turing machines, transition systems, and interaction
Information and Computation
A mathematical model for Cantor coding in the hippocampus
Neural Networks
| Hi-index | 0.00 |
In classical computation, rational-and real-weighted recurrent neural networks were shown to be respectively equivalent to and strictly more powerful than the standard Turing machine model. Here, we study the computational power of recurrent neural networks in a more biologically oriented computational framework, capturing the aspects of sequential interactivity and persistence of memory. In this context, we prove that so-called interactive rational-and real-weighted neural networks show the same computational powers as interactive Turing machines and interactive Turing machines with advice, respectively. A mathematical characterization of each of these computational powers is also provided. It follows from these results that interactive real-weighted neural networks can perform uncountably many more translations of information than interactive Turing machines, making them capable of super-Turing capabilities.