Energy Complexity of Recurrent Neural Networks

DOI10.1162/NECO_a_00579zbMath1416.92020OpenAlexW1978903553WikidataQ47751171 ScholiaQ47751171MaRDI QIDQ5378352

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)

Related Items (6)

Energy complexity of satisfying assignments in monotone circuits: on the complexity of computing the best case ⋮ Subrecursive neural networks ⋮ Computing the best-case energy complexity of satisfying assignments in monotone circuits ⋮ Three analog neurons are Turing universal ⋮ Quasi-periodic \(\beta\)-expansions and cut languages ⋮ Analog neuron hierarchy

Cites Work

• Unnamed Item
• Unnamed Item
• Energy and depth of threshold circuits
• Size-energy tradeoffs for unate circuits computing symmetric Boolean functions
• Exponential lower bounds on the size of constant-depth threshold circuits with small energy complexity
• Computing with truly asynchronous threshold logic networks
• On the computational power of neural nets
• Energy and Fan-In of Threshold Circuits Computing Mod Functions
• Lower Bounds for Linear Decision Trees via an Energy Complexity Argument
• On the Computational Power of Threshold Circuits with Sparse Activity
• Theory of neuromata
• Efficient simulation of finite automata by neural nets
• Optimal simulation of automata by neural nets
• General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results
• Communication Complexity
• Computational Work and Time on Finite Machines

This page was built for publication: Energy Complexity of Recurrent Neural Networks