AbstractThe rapid development of brain‐inspired computing requires new artificial components and architectures for its hardware implementation. In this regard, memristive devices emerged as potential candidates for artificial synapses because of their ability to emulate the plasticity of the biological synapses. In this work, the synaptic behavior of the TiN/La2NiO4+δ/Pt memristive devices based on thermally annealed La2NiO4+δ films is thoroughly investigated. Using electron energy loss spectroscopy (EELS), it is shown that post‐deposition annealing using inert (Ar) or oxidizing (O2) atmospheres affects the interstitial oxygen content (δ) in the La2NiO4+δ films. Electrical characterization shows that both devices exhibit long‐term potentiation/depression (LTP/LTD) and spike‐timing‐dependent plasticity (STDP). At the same time, the Ar annealed TiN/La2NiO4+δ/Pt device demonstrates filamentary‐like behavior, fast switching, and low energy consumption. On the other hand, the O2 annealed TiN/La2NiO4+δ/Pt devices are forming‐free, exhibiting interfacial‐like resistive switching with slower kinetics. Finally, the simulation tools show that spiking neural network (SNN) architectures with weight updates based on the experimental data achieve high inference accuracy in the digit recognition task, which proves the potential of TiN/La2NiO4+δ/Pt devices for artificial synapse applications.
Read full abstract