.png){kind=icon}
.png){kind=icon}
Return
A Continuous Time Dynamical Turing Machine
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2024.3397995.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Continuous time recurrent neural networks (CTRNNs) are systems of coupled ordinary differential equations (ODEs) inspired by the structure of neural networks in the brain. CTRNNs are known to be universal dynamical approximators: given a large enough system, the parameters of a CTRNN can be tuned to produce output that is arbitrarily close to that of any other dynamical system. However, in practice, both designing systems of CTRNN to have a certain output, and the reverse-understanding the dynamics of a given system of CTRNN-can be nontrivial. In this article, we describe a method for embedding any specified Turing machine in its entirety into a CTRNN. As such, we describe in detail a continuous time dynamical system that performs arbitrary discrete-state computations. We suggest that in acting as both a continuous time dynamical system and as a computer, the study of such systems can help refine and advance the debate concerning the Computational Hypothesis that cognition is a form of computation and the Dynamical Hypothesis that cognitive systems are dynamical systems.
Keywords:
Dynamical systems
Turing machines
Cognition
Neurons
Symbols
Biological neural networks
Assembly
Continuous time recurrent neural network (CTRNN)
network attractor
Turing machine
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W