Agent-environment approach to the simulation of turing machines by neural networks

Proceedings of the International Joint Conference on Neural Networks

Volumn 1, Issue , 2001, Pages 71-76

  De Oliveira, W R ^a   De Souto, M C P ^a   Ludermir, T B ^a  

^a UNIVERSIDADE FEDERAL RURAL DE PERNAMBUCO   (Brazil)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SIMULATION; FUNCTIONS; INTELLIGENT AGENTS; TURING MACHINES;

AGENT-ENVIRONMENT APPROACH; CONTROL MODULE; DISCRETE TIME RECURRENT NEURAL NETWORK; FINITE STATE CONTROL; MOVEMENT MODULE; RECOGNITION MODULE; WRITING MODULE;

RECURRENT NEURAL NETWORKS;

EID: 0034854314     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. Stable encoding of finite-state machines in discrete-time recurrent neural nets with sigmoid units
2. Turing machine simulation by logical neural networks
3. Neural computability
4. First-order vs. second-order single layer recurrent neural networks
5. Situativity and symbols: Response to Vera and Simon
6. A comparison of the computational power of neural network models
7. Analog neural nets with Gaussian or other common noise distributions cannot recognize arbitrary regular languages
8. A logical calculus of the ideas immanent in nervous activity
9. Small universal turing machines
10. Computational capabilities of recurrent NARX neural networks
11. On the computational power of neural nets
12. Turing equivalence of neural networks with second order connection weights
13. On computable numbers with an application to the Entscheidungsproblem
14. Situated action: A symbolic interpretation
15. Turing's analysis of computation and theories of cognit-ve architecture