In the era of artificial intelligence and smart automated systems, the quest for efficient data processing has driven exploration into neuromorphic systems, aiming to replicate brain functionality and complex cognitive actions. This review assesses, based on recent literature, the challenges and progress in developing basic neuromorphic systems, focusing on “material-neuron” concepts, that integrate structural similarities, analog memory, retention, and Hebbian learning of the brain, contrasting with conventional von Neumann architecture and spiking circuits. We categorize these devices into filamentary and non-filamentary types, highlighting their ability to mimic synaptic plasticity through external stimuli manipulation. Additionally, we emphasize the importance of heterogeneous neural content to support conductance linearity, plasticity, and volatility, enabling effective processing and storage of various types of information. Our comprehensive approach categorizes fundamentally different devices under a generalized pattern dictated by the driving parameters, namely, the pulse number, amplitude, duration, interval, as well as the current compliance employed to contain the conducting pathways. We also discuss the importance of hybridization protocols in fabricating neuromorphic systems making use of existing complementary metal oxide semiconductor technologies being practiced in the silicon foundries, which perhaps ensures a smooth translation and user interfacing of these new generation devices. The review concludes by outlining insights into developing cognitive systems, current challenges, and future directions in realizing deployable neuromorphic systems in the field of artificial intelligence.

中文翻译：

---

非冯·诺依曼神经形态系统在材料计算和认知功能方面的最新趋势


在人工智能和智能自动化系统时代，对高效数据处理的追求推动了对神经形态系统的探索，旨在复制大脑功能和复杂的认知行为。本综述根据最近的文献评估了开发基本神经形态系统的挑战和进展，重点关注“材料-神经元”概念，这些概念整合了结构相似性、模拟记忆、保留和大脑的赫布学习，与传统的冯·诺依曼架构和尖峰电路形成鲜明对比。我们将这些设备分为丝状和非丝状类型，突出了它们通过外部刺激操作模拟突触可塑性的能力。此外，我们强调了异质神经内容对支持电导线性、可塑性和波动性的重要性，从而能够有效处理和存储各种类型的信息。我们的综合方法将基本不同的器件分类为由驱动参数决定的广义模式，即脉冲数、振幅、持续时间、间隔以及用于包含导电路径的电流柔度。我们还讨论了杂交协议在利用硅代工厂正在实践的现有互补金属氧化物半导体技术制造神经形态系统方面的重要性，这也许可以确保这些新一代器件的顺利转换和用户接口。综述最后概述了对在人工智能领域实现可部署神经形态系统的发展认知系统、当前挑战和未来方向的见解。