Positive neural networks in discrete time implement monotone-regular behaviors

DOI10.1162/NECO_A_00789MaRDI QIDQ5380357zbMATH OpenDBLPWikidataFDO

Authors Tom J. Ameloot, Jan Van den Bussche

Publication date 4 June 2019

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1502.06094

zbMATH Keywords

connection weightsdiscrete timemonotone-regular behaviorpositive neural networks

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: We study the expressive power of positive neural networks. The model uses positive connection weights and multiple input neurons. Different behaviors can be expressed by varying the connection weights. We show that in discrete time, and in absence of noise, the class of positive neural networks captures the so-called monotone-regular behaviors, that are based on regular languages. A finer picture emerges if one takes into account the delay by which a monotone-regular behavior is implemented. Each monotone-regular behavior can be implemented by a positive neural network with a delay of one time unit. Some monotone-regular behaviors can be implemented with zero delay. And, interestingly, some simple monotone-regular behaviors can not be implemented with zero delay.

Recommendations

• Positive automata networks
• Artificial Intelligence and Soft Computing - ICAISC 2004
• scientific article; zbMATH DE number 2242764
• Global dynamics of discrete neural networks allowing non-monotonic activation functions
• Symmetric discrete universal neural networks

Cites work

• Constructing deterministic finite-state automata in recurrent neural networks
• Efficient simulation of finite automata by neural nets
• General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results
• scientific article; zbMATH DE number 1809722 (Why is no real title available?)
• scientific article; zbMATH DE number 5595162 (Why is no real title available?)
• scientific article; zbMATH DE number 3664335 (Why is no real title available?)
• scientific article; zbMATH DE number 872005 (Why is no real title available?)
• Links between probabilistic automata and hidden Markov models: probability distributions, learning models and induction algorithms
• Lower Bounds for the Computational Power of Networks of Spiking Neurons
• Monotone circuits for monotone weighted threshold functions
• On the Classification Capability of Sign-Constrained Perceptrons
• On the computational power of neural nets
• Optimal simulation of automata by neural nets
• The monotone circuit complexity of Boolean functions
• Theory of neuromata

Cited in

(5)

• \(\ell_1\)-gain filter design of discrete-time positive neural networks with mixed delays
• Robust exponential stabilization of positive uncertain switched neural networks with actuator saturation and sensor faults
• Positive solutions and exponential stability of nonlinear time-delay systems in the model of BAM-Cohen-Grossberg neural networks
• Exponential attractivity of positive inertial neural networks in bidirectional associative memory model with heterogeneous delays
• Finite-time bumpless transfer synchronisation of discrete-time delayed positive neural networks under dual-channel false data inject attacks

This page was built for publication: Positive neural networks in discrete time implement monotone-regular behaviors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380357)