## References and models cited by this paper | ## References and models that cite this paper | |

Ackley DH, Hinton GE, Sejnowski TJ (1985) A learning algorithm for Bolzmann machines. Allender E (1989) A note on the power of threshold circuits Alon N (1985) Asynchronous threshold networks Alon N, Bruck J (1994) Explicit construction of depth-2 majority circuits for comparison and addition Alon N, Dewdney AK, Ott TJ (1991) Efficient simulation of finite automata by neural nets Balcazar JL, Diaz J, Gabarro J (1995) Balcazar JL, Gavalda R, Siegelmann HT (1997) Computational power of neural networks: A characterization in terms of Kolmogorov complexity Balcazar JL, Hermo M (1998) The structure of logarithmic advice complexity classes Barahona F (1982) On the computational complexity of I sing spin glass models Ben-hur A, Siegelmann HT, Fishman S (2002) A theory of complexity for continuous time systems Bertoni A, Campadelli P (1994) On the approximability of the energy function Bertoni A, Campadelli P, Gangai C, Posenato R (1997) Approximability of the ground state problem for certain I sing spin glasses Bieche I, Maynard R, Rammal R, Uhry JP (1980) On the ground states of the frustration model of a spin glass by a matching method of graph theory Bovet DP, Crescenzi P (1994) Bruck J, Goodman JW (1988) A generalized convergence theorem for neural networks Casey M (1996) The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction. Chandra AK, Stockmeyer LJ, Vishkin U (1984) Constant depth reducibility Cohen M, Grossberg S (1983) Absolute stability of global pattern formation and parallel memory storage by competitive neural network. Cover T (1965) Geometric and statistical properties of systems of linear in-equalities with applications in pattern recognition Cover TM (1968) Capacity problems for linear machines Dasgupta B, Schnitger G (1993) The power of approximating:A comparison of activation functions DasGupta B, Schnitger G (1996) Analog versus discrete neural networks. Floreen P (1991) Worst-case convergence times for Hopfield memories. Floreen P, Orponen P (1989) On the computational complexity of analyzing Hopfield nets Floreen P, Orponen P (1993) Attraction radii in Hopfield nets are hard to compute Floreen P, Orponen P (1994) Complexity issues in discrete Hopfield networks Fogelman F, Goles E, Weisbuch G (1983) Transient length in sequential iterations of threshold functions Fogelman-Soulie F, Mejia C, Goles E, Martinez S (1989) Energy functions in neural networks with continuous local functions Furst M, Saxe JB, Sipser M (1984) Parity, circuits and the polynomial-time hierarchy Garey MR, Johnson DS (1979) Godbeer GH, Lipscomb J, Luby M (1988) On the computational complexity of finding stable state vectors in connectionist models (Hopfield nets) Goemans MX, Williamson DP (1995) Improved approximate algorithms for maximum cut and satisfiability problems using semidefinite programming Goldmann M, Hastad J, Razborov A (1992) Majority gates vs. general weighted threshold gates Goldmann M, Karpinski M (1998) Simulating threshold circuits by majority circuits Goldschlager LM, Parberry I (1986) On the construction of parallel computers from various bases of Boolean functions Goles E (1985) Dynamics of positive automata networks Goles E (1987) Lyapunov functions associated to automata networks Goles E, Martinez S (1989) Exponential transient classes of symmetric neural networks for synchronous and sequential updating Goles E, Martinez S (1990) Goles E, Olivos J (1981) Comportement periodique des fonctions a seuilbinaires et applications Goles E, Olivos J (1981) The convergence of symmetric threshold automata Goles-chacc E, Fogelman-Soulie F, Pellegrin D (1985) Decreasing energy functions as a tool for studying threshold networks Gori M, Meer K (2002) A step towards a complexity theory for analog systems Hajnal A, Maass W, Pudlak P, Szegedy M, Turan G (1993) Threshold circuits of bounded depth Haken A (1989) Connectionist networks that need exponential time to stabilize Haken A, Luby M (1988) Steepest descent can take exponential time for symmetric connectionist networks Hammer PL, Ibaraki T, Peled UN (1981) Threshold numbers and threshold completions Hartley R, Szu H (1987) A comparison of the computational power of neural network models Hastad J (1989) Almost optimal lower bounds for small depth circuits Hastad J (1994) On the size of weights for threshold gates Hegedus T, Megiddo N (1996) On the geometric separability of Boolean functions Hofmeister T (1994) Depth-efficient threshold circuits for arithmetic functions Hofmeister T, Hohberg W, Kohling S (1991) Some notes on threshold circuits, and multiplication in depth 4 Hofmeister T, Pudlak P (1992) A proof that division is not in TC02 Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Hopfield JJ, Tank DW (1985) "Neural" computation of decisions in optimization problems. Horne BG, Hush DR (1994) On the node complexity of neural networks Horne BG, Hush DR (1996) Bounds on the complexity of recurrent neural network implementations of finite state machines Indyk P (1995) Optimal simulation of automata by neural nets Irmatov AA (1996) Bounds for the number of threshold functions Johnson DS, Papadimitriou CH, Yannakakis M (1988) How easy is local search? Kahn J (1995) On the probability that a random 1 n matrix is singular Kilian J, Siegelmann HT (1996) The dynamic universality of sigmoidal neural networks Kleene SC (1956) Representation of events in nerve nets and finite automata Kohonen T (2001) Koiran P (1994) Dynamics of discrete time, continuous state Hopfield networks Koiran P (1996) A family of universal recurrent networks Komlos J, Paturi R (1988) Convergence results in an associative memory model Legenstein RA, Maass W (2001) Foundations for a circuit complexity theory of sensory processing Lepley M, Miller G (1983) Computational power for networks of threshold devices in asynchronous environment Lipscomb J (1987) On the computational complexity of finding a connectionist models stable state vectors Lupanov OB (1961) Implementing the algebra of logic functions in terms of bounded depth formulas in the basis Lupanov OB (1972) Circuits using threshold elements Maass W (1995) On the computational complexity of networks of spiking neurons Maass W (1996) On the computational power of noisy spiking neurons Maass W (1996) Networks of spiking neurons: The third generation of neural network models Maass W (1996) Lower bounds for the computational power of networks of spiking neurons Maass W (1997) Fast sigmoidal networks via spiking neurons. Maass W (1997) Bounds for the computational power and learning complexity of analog neural nets Maass W (2000) On the computational power of winner-take-all. Maass W, Bishop CM (1999) Maass W, Natschlager T (1997) Networks of spiking neurons can emulate arbitrary Hopfield nets in temporal coding Maass W, Natschläger T (2000) A model for fast analog computation based on unreliable synapses. Maass W, Orponen P (1998) On the effect of analog noise in discrete-time analog computations Maass W, Ruf B (1999) On computation with pulses Maass W, Schmitt M (1999) On the complexity of learning for spiking neurons with temporal coding Maass W, Schnitger G, Sontag ED (1991) On the computational power of sigmoid versus Boolean threshold circuits Maass W, Sontag ED (1999) Analog neural nets with gaussian or other common noise distribution cannot recognize arbitrary regular languages. Mahajan S, Ramesh H (1999) Derandomizing approximation algorithms based on semidefinite programming Mceliece RJ, Posner EC, Rodemich ER, Venkatesh SS (1987) The capacity of the Hopfield associative memory Minsky M (1969) Minsky ML (1967) Moore C (1998) Finite-dimensional analog computers: flows, maps, and recurrent neural networks Muroga S (1971) Muroga S, Toda I, Takasu S (1961) Theory of majority decision elements Nechiporuk EI (1964) The synthesis of networks from threshold elements Oneil PE (1971) Hyperplane cuts of an n-cube Orponen P (1994) Computational complexity of neural networks: A survey Orponen P (1996) The computational power of discrete Hopfield nets with hidden units Orponen P (1997) Computing with truly asynchronous threshold logic networks Orponen P (1997) The computational power of continuous time neural networks Orponen P (1997) A survey of continuous-time computation theory Orponen P (2000) An overview of the computational power of recurrent neural networks Papadimitriou CH (1994) Parberry I (1990) A primer on the complexity theory of neural networks Parberry I (1994) Parberry I, Schnitger G (1989) Relating Boltzmann machines to conventional models of computation Poljak S, Sura M (1983) On periodical behaviour in societies with symmetric influences Porat S (1989) Stability and looping in connectionist models with asymmetric weights Powell MJD (1985) Radial basis functions for multivariable interpolation: A review Rabin MO (1963) Probabilistic automata Razborov AA (1992) On small depth threshold circuits Reif JH, Tate SR (1992) On threshold circuits and polynomial computations ROSENBLATT F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Roychowdhury VP, Siu KY, Orlitsky A (1994) Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Savage JE (1972) Computational work and time on finite machines Savage JE (1998) Schaffer AA, Yannakakis M (1991) Simple local search problems that are hard to solve Schlafli L (1901) Schmitt M (1998) On computing Boolean functions by a spiking neuron Schmitt M (2002) Descartes' rule of signs for radial basis function neural networks. Siegelmann H, Sontag E (1995) On the computational power of neural nets Siegelmann H, Sontag ED (1994) Analog computation via neural networks Siegelmann HT (1994) Onthe computational power of probabilistic and faulty neural networks Siegelmann HT (1996) Recurrent neural networks and finite automata Siegelmann HT (1999) Siegelmann HT (1999) Stochastic analog networks and computational complexity Siegelmann HT, Roitershtein A, Ben-hur A (2000) Noisy neural networksand generalizations Sima J (1995) Hopfield languages Sima J (1997) Analog stable simulation of discrete neural networks Sima J (2001) The computational capabilities of neural networks (extended abstract) Sima J, Orponen P (2000) A continuous-time Hopfield net simulation of discrete neural networks Sima J, Orponen P (2001) Exponential transients in continuous-time symmetric Hopfield nets Síma J, Orponen P (2003) Continuous-time symmetric Hopfield nets are computationally universal. Sima J, Orponen P, Antti-Poika T (2000) On the computational complexity of binary and analog symmetric hopfield nets Sima J, Wiedermann J (1998) Theory of neuromata Siu KY, Bruck J, Kailath T, Hofmeister T (1993) Depth efficient neural networks for division and related problems Siu KY, Roychowdhury V, Kailath T (1995) Siu KY, Roychowdhury VP (1994) On optimal depth threshold circuits for multiplication and related problems Siu KY, Roychowdhury VP, Kailath T (1991) Depth-size tradeoffs for neural computation Siu KY, Roychowdhury VP, Kailath T (1993) Computing with almost optimal size neural networks Siu KY, Roychowdhury VP, Kailath T (1994) Rational approximation techniques for analysis of neural networks Siu KY, Roychowdhury VP, Kailath T (1995) Toward massively parallel design of multipliers Sorel M, Sima J (2000) Robust implementation of finite automata by recurrent RBF networks Tanaka F, Edwards SF (1980) Analytic theory of the ground state properties of a spin glass: I. Ising spin glass Tchuente M (1986) Sequential simulation of parallel iterations and applications Vollmer H (1999) von_Neumann J (1956) Wegener I (1987) Wegener I (1993) Optimal lower bounds on the depth of polynomial-size threshold circuits for some arithmetic functions Werbos PJ (1974) Beyond regression: New tools for prediction and analysis in the behavioral sciences Wiedermann J (1994) Complexity issues in discrete neurocomputing Yao ACC (1985) Separating the polynomial time hierarchy by oracles Yuille AL, Geiger D (2003) Winner-take-all networks |