Biopolymer based artificial synapses enable linear conductance tuning and low-power for neuromorphic computing
Ke Zhang, Qi Xue, Chao Zhou, Wanneng Mo, Chun‐Chao Chen, Ming Li, Tao Hang
Abstract
is doped to ι-car to suppress the formation of Ag filaments, thereby eliminating uneven Joule heating. Using deep learning of hand-written digits as an application, a doping-enhanced recognition accuracy (93.8%) is achieved, close to that of an ideal synaptic device (95.7%). This work verifies the feasibility of using biopolymers for future high-performance computational and wearable/implantable electronic applications.
Topics & Concepts
Neuromorphic engineeringMemristorBottleneckArtificial neural networkMaterials scienceConductanceComputer scienceVon Neumann architectureElectronic engineeringPower (physics)DopingArtificial intelligenceNanotechnologyOptoelectronicsPhysicsEngineeringEmbedded systemCondensed matter physicsOperating systemQuantum mechanicsAdvanced Memory and Neural ComputingPhotoreceptor and optogenetics researchTransition Metal Oxide Nanomaterials