Energy complexity of recurrent neural networks

DOI10.1162/NECO_A_00579MaRDI QIDQ5378352zbMATHOpenAlexWikidataFDO

Authors Jiří Šíma

Publication date 12 June 2019

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco_a_00579

zbMATH Keywords

finite automatonrecurrent neural networksenergy complexity measure

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Energy-Time Tradeoff in Recurrent Neural Nets
• Energy Complexity and Entropy of Threshold Circuits
• On the Computational Power of Threshold Circuits with Sparse Activity
• Exponential lower bounds on the size of constant-depth threshold circuits with small energy complexity
• Lower bounds for threshold circuits of bounded energy

Cites work

• scientific article; zbMATH DE number 3310089 (Why is no real title available?)
• scientific article; zbMATH DE number 3419055 (Why is no real title available?)
• Communication Complexity
• Computational Work and Time on Finite Machines
• Computing with truly asynchronous threshold logic networks
• Efficient simulation of finite automata by neural nets
• Energy and depth of threshold circuits
• Energy and fan-in of threshold circuits computing mod functions
• Exponential lower bounds on the size of constant-depth threshold circuits with small energy complexity
• General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results
• Lower bounds for linear decision trees via an energy complexity argument
• On the Computational Power of Threshold Circuits with Sparse Activity
• On the computational power of neural nets
• Optimal simulation of automata by neural nets
• Size-energy tradeoffs for unate circuits computing symmetric Boolean functions
• Theory of neuromata

Cited in

(8)

• Three analog neurons are Turing universal
• Energy-Time Tradeoff in Recurrent Neural Nets
• Energy complexity of satisfying assignments in monotone circuits: on the complexity of computing the best case
• Analog neuron hierarchy
• Subrecursive neural networks
• Relations between energy complexity measures of Boolean networks and positive sensitivity of Boolean functions
• Computing the best-case energy complexity of satisfying assignments in monotone circuits
• Quasi-periodic \(\beta\)-expansions and cut languages

This page was built for publication: Energy complexity of recurrent neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5378352)