Analog neural nets with Gaussian or other common noise distributions cannot recognize arbitary regular languages

Authors:
Wolfgang Maass;Eduardo D. Sontag
Affiliations:
-;-
Venue:
Neural Computation
Year:
1999

Citing 3
Cited 13

Invariance of complexity measures for networks with unreliable gates

Journal of the ACM (JACM)
Constructing deterministic finite-state automata in recurrent neural networks

Journal of the ACM (JACM)
The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction

Neural Computation

Transcending Turing Computability

Minds and Machines
Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation
What Will Be Eventually True of Polynomial Hybrid Automata?

TACS '01 Proceedings of the 4th International Symposium on Theoretical Aspects of Computer Software
Continuous-time symmetric Hopfield nets are computationally universal

Neural Computation
Recurrent neural networks with small weights implement definite memory machines

Neural Computation
General-purpose computation with neural networks: a survey of complexity theoretic results

Neural Computation
Incremental training of first order recurrent neural networks to predict a context-sensitive language

Neural Networks
On probabilistic analog automata

Theoretical Computer Science
On the computational power of circuits of spiking neurons

Journal of Computer and System Sciences
Cognition and the Power of Continuous Dynamical Systems

Minds and Machines
Stable Encoding of Finite-State Machines in Discrete-Time Recurrent Neural Nets with Sigmoid Units

Neural Computation
Computational processes, observers and Turing incompleteness

Theoretical Computer Science
Computation with perturbed dynamical systems

Journal of Computer and System Sciences

Quantified Score

Hi-index	0.00

Visualization

Abstract