Analog computation via neural networks

DOI10.1016/0304-3975(94)90178-3zbMath0822.68029OpenAlexW2050778826WikidataQ55897750 ScholiaQ55897750MaRDI QIDQ1331940

Eduardo D. Sontag, Hava T. Siegelmann

Publication date: 18 October 1995

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0304-3975(94)90178-3

zbMATH Keywords

analog computation neural networks

Mathematics Subject Classification ID

Related Items

A refutation of Penrose's Gödelian case against artificial intelligence, Computing over the reals with addition and order, Edge of chaos and prediction of computational performance for neural circuit models, On the computational power of dynamical systems and hybrid systems, The simple dynamics of super Turing theories, A family of universal recurrent networks, Global exponential convergence and global convergence in finite time of non-autonomous discontinuous neural networks, Recurrent Neural Networks with Small Weights Implement Definite Memory Machines, The Computational Power of Interactive Recurrent Neural Networks, General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results, Computation with perturbed dynamical systems, Unnamed Item, AN ANALOGUE-DIGITAL CHURCH-TURING THESIS, The promise of analog computation, A note on discreteness and virtuality in analog computing, Simulation of Turing machine with uEAC-computable functions, Automata theory based on quantum logic: Some characterizations, Dynamical recognizers: real-time language recognition by analog computers, Expressive Power of Non-deterministic Evolving Recurrent Neural Networks in Terms of Their Attractor Dynamics, The ARNN model relativises \(\mathrm{P}=\mathrm{NP}\) and \(\mathrm{P}\neq \mathrm{NP}\), Subrecursive neural networks, On Goles' universal machines: a computational point of view, Three analog neurons are Turing universal, Design of continuous-time recurrent neural networks with piecewise-linear activation function for generation of prescribed sequences of bipolar vectors, The Kolmogorov-Arnold representation theorem revisited, Computations with oracles that measure vanishing quantities, The Power of Machines That Control Experiments, A provably stable neural network Turing machine with finite precision and time, The expressive power of analog recurrent neural networks on infinite input streams, Quasi-periodic \(\beta\)-expansions and cut languages, Computational capabilities of analog and evolving neural networks over infinite input streams, Finite time convergent learning law for continuous neural networks, On the computational power of discrete Hopfield nets, The modal argument for hypercomputing minds, Hypercomputation: Philosophical issues, Analog computation through high-dimensional physical chaotic neuro-dynamics, On the computational power of probabilistic and faulty neural networks, Automata complete computation with Hodgkin-Huxley neural networks composed of synfire rings, Analog neuron hierarchy, A weak version of the Blum, Shub, and Smale model, On the computation of Boolean functions by analog circuits of bounded fan-in, Iteration, inequalities, and differentiability in analog computers, A survey of computational complexity results in systems and control, Interval-valued computations and their connection with PSPACE, Cut Languages in Rational Bases, Generalized Lyapunov approach for convergence of neural networks with discontinuous or non-Lipschitz activations, The stability of saturated linear dynamical systems is undecidable, Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations, A new Gödelian argument for hypercomputing minds based on the busy beaver problem, The case for hypercomputation, How much can analog and hybrid systems be proved (super-)Turing, Analog computation beyond the Turing limit, The many forms of hypercomputation, An optical model of computation, Expressive power of first-order recurrent neural networks determined by their attractor dynamics, Continuous-Time Symmetric Hopfield Nets Are Computationally Universal, Vapnik-Chervonenkis dimension of recurrent neural networks, Computing with truly asynchronous threshold logic networks, On digital nondeterminism, Closed-form analytic maps in one and two dimensions can simulate universal Turing machines, The structure of logarithmic advice complexity classes, Quantum automata and quantum grammars, Frontier between decidability and undecidability: A survey, THE MYTH OF 'THE MYTH OF HYPERCOMPUTATION', Stochastic analog networks and computational complexity, Logic and Complexity in Cognitive Science, Analog computation with dynamical systems, A theory of complexity for continuous time systems, Continuous-Time Symmetric Hopfield Nets Are Computationally Universal, A Survey on Analog Models of Computation

Cites Work