6533b7d5fe1ef96bd1264f44
RESEARCH PRODUCT
The computational power of continuous time neural networks
Pekka Orponensubject
TheoryofComputation_COMPUTATIONBYABSTRACTDEVICESQuantitative Biology::Neurons and CognitionComputational complexity theoryArtificial neural networkComputer sciencebusiness.industryComputer Science::Neural and Evolutionary ComputationNSPACEComputational resourcePower (physics)Turing machinesymbols.namesakeCellular neural networksymbolsArtificial intelligenceTypes of artificial neural networksbusinessdescription
We investigate the computational power of continuous-time neural networks with Hopfield-type units. We prove that polynomial-size networks with saturated-linear response functions are at least as powerful as polynomially space-bounded Turing machines.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 1997-01-01 |