RESUMEN
With the evolution of artificial intelligence, the explosive growth of data from sensory terminals gives rise to severe energy-efficiency bottleneck issues due to cumbersome data interactions among sensory, memory, and computing modules. Heterogeneous integration methods such as chiplet technology can significantly reduce unnecessary data movement; however, they fail to address the fundamental issue of the substantial time and energy overheads resulting from the physical separation of computing and sensory components. Brain-inspired in-sensor neuromorphic computing (ISNC) has plenty of room for such data-intensive applications. However, one key obstacle in developing ISNC systems is the lack of compatibility between material systems and manufacturing processes deployed in sensors and computing units. This study successfully addresses this challenge by implementing fully CMOS-compatible TiN/HfOx-based neuristor array. The developed ISNC system demonstrates several advantageous features, including multilevel analogue modulation, minimal dispersion, and no significant degradation in conductance (@125 °C). These characteristics enable stable and reproducible neuromorphic computing. Additionally, the device exhibits modulatable sensory and multi-store memory processes. Furthermore, the system achieves information recognition with a high accuracy rate of 93%, along with frequency selectivity and notable activity-dependent plasticity. This work provides a promising route to affordable and highly efficient sensory neuromorphic systems.
Asunto(s)
Inteligencia Artificial , Sustancias Explosivas , Encéfalo , Comercio , MovimientoRESUMEN
The ultimate aim of artificial synaptic devices is to mimic the features of biological synapses as closely as possible, in particular, its ability of self-adjusting the synaptic weight responding to the external stimulus. In this work, memristors, based on trilayer oxides with a stack structure of TiN/TiON/HfOy/HfOx/TiN, are designed to function as the artificial synapses where intrinsically designed oxygen-deficient HfOx layer, less oxygen-deficient HfOy layer, and TiON layer, imitating the corresponding biological functionality of the pre-synapse, synaptic cleft, and post-synapse, respectively, resemble the features of bio-synapses most closely. Thus, diverse bio-synaptic functions and plasticity, including long-term potentiation and depression, spike-rate-dependent plasticity, spike-timing-dependent plasticity, and metaplasticity, are fulfilled in these devices. Moreover, they exhibit analogue plasticity in both potentiating and depressing, fully emulating the learning protocols of excitation and inhibition in the bio-synapses. The structure and Hf/O distribution of these devices, mimicking the structure and Ca2+ deployment of bio-synapses, are consolidated by the high-resolution transmission electron microscopy and energy-dispersive X-ray spectroscopy, respectively. Powerful bio-realistic behavior, implemented in these simple artificial synaptic devices, make them tailored for neuromorphic hardware applications.