Heterogeneous reservoir computing in second-order Ta<sub>2</sub>O<sub>5</sub>/HfO<sub>2</sub> memristors
N. Ghenzi, Tae Won Park, Seung Soo Kim, Hae Jin Kim, Yoon Ho Jang, Kyung Seok Woo, Cheol Seong Hwang
Abstract
memristor system present different behaviors in agreement with its history-dependent conductance and allow the fine-tuning of the behavior of each reservoir unit. The heterogeneity in the reservoir units improves the pattern recognition performance in the heterogeneous memristor RC system with a similar physical structure.
Topics & Concepts
MemristorReservoir computingNonlinear systemBilayerHomogeneousMaterials scienceResistive random-access memoryConductanceComputer sciencePhysicsElectronic engineeringStatistical physicsCondensed matter physicsElectrodeArtificial intelligenceChemistryArtificial neural networkEngineeringRecurrent neural networkQuantum mechanicsMembraneBiochemistryAdvanced Memory and Neural ComputingNeural Networks and Reservoir ComputingNeural dynamics and brain function