Configurable NbO<sub>x</sub> Memristors as Artificial Synapses or Neurons Achieved by Regulating the Forming Compliance Current for the Spiking Neural Network

Han, Chuanyu; Fang, Sheng; Cui, Yi Lin; Liu, Weihua; Fan, Shi Quan; Huang, Xueli; Li, Xin; Wang, Xiao Li; Zhang, Guohe; Tang, Wing Man; Lai, Po‐Chien; Lu, Jia; Wan, Xianjie; Zhou, Yu; Geng, Li

doi:10.1002/aelm.202300018

Cited by 11 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classical Pavlov learning was demonstrated using spike based response signals (see Figure 7 a–c) by C.Y. Han et al [ 161 ]. They used a reconfigurable memristor device based on NbO x switching layer as both the synapse and neuron to trigger a threshold spiking behavior, as shown in Figure 7 b,c.…”

Section: Emerging Neuromorphic Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Resistive Switching Devices for Neuromorphic Computing: From Foundations to Chip Level Innovations

Udaya Mohanan

2024

Nanomaterials

View full text Add to dashboard Cite

Neuromorphic computing has emerged as an alternative computing paradigm to address the increasing computing needs for data-intensive applications. In this context, resistive random access memory (RRAM) devices have garnered immense interest among the neuromorphic research community due to their capability to emulate intricate neuronal behaviors. RRAM devices excel in terms of their compact size, fast switching capabilities, high ON/OFF ratio, and low energy consumption, among other advantages. This review focuses on the multifaceted aspects of RRAM devices and their application to brain-inspired computing. The review begins with a brief overview of the essential biological concepts that inspire the development of bio-mimetic computing architectures. It then discusses the various types of resistive switching behaviors observed in RRAM devices and the detailed physical mechanisms underlying their operation. Next, a comprehensive discussion on the diverse material choices adapted in recent literature has been carried out, with special emphasis on the benchmark results from recent research literature. Further, the review provides a holistic analysis of the emerging trends in neuromorphic applications, highlighting the state-of-the-art results utilizing RRAM devices. Commercial chip-level applications are given special emphasis in identifying some of the salient research results. Finally, the current challenges and future outlook of RRAM-based devices for neuromorphic research have been summarized. Thus, this review provides valuable understanding along with critical insights and up-to-date information on the latest findings from the field of resistive switching devices towards brain-inspired computing.

show abstract

Section: Emerging Neuromorphic Applicationsmentioning

confidence: 99%

“…Electrical voltage output ( b ) before the training process & ( c ) after the training process. Reprinted with permission under a Creative Commons CCBY License from [ 161 ]. ( d ) Schematic of the VGG8 neural network architecture used for CIFAR-10 pattern recognition using a GeO x -based RRAM cell.…”

Section: Figurementioning

confidence: 99%

Resistive Switching Devices for Neuromorphic Computing: From Foundations to Chip Level Innovations

Udaya Mohanan

2024

Nanomaterials

View full text Add to dashboard Cite

show abstract

Secondary Order RC Sensor Neuron Circuit for Direct Input Encoding in Spiking Neural Network

Yang,

Li,

Feng

et al. 2024

Adv Elect Materials

View full text Add to dashboard Cite

In spiking neural networks (SNNs), artificial sensor neurons are crucial for converting real‐world analog information into encoded spikes. However, existing SNNs face challenges due to the inefficient implementation of input sensor neurons. Here, this study proposes an SNN‐compatible spike mode sensor, designed to directly convert analog current signals into real‐time encoded spikes, feeding the SNN concurrently. The input sensor neuron is realized using a stable neuron circuit employing a threshold switching (TS) memristor and secondary order RC block. This design enables time delay‐free spike firing, operates at low voltage, and offers a wide signal sensing range. Furthermore, this study presents an expression delineating the relationship between the pulse emission properties of the circuit and the parameters of its components, laying the basis for circuit components design and development. Analytical analysis confirms the sensor's efficacy in implementing rate‐based and time‐to‐first spike encoding schemes. Integrating the sensor into SNNs as the input layer for image training and recognition tasks yields an impressive accuracy of 87.58% on the MNIST dataset, showcasing its applicability as a crucial interface between the physical world and the SNN framework.

show abstract

Flexible Printed Ultraviolet‐to‐Near‐Infrared Broadband Optoelectronic Carbon Nanotube Synaptic Transistors for Fast and Energy‐Efficient Neuromorphic Vision Systems

Li,

Zhu

et al. 2024

Small Methods

View full text Add to dashboard Cite

To simulate biological visual systems and surpass their functions and performance, it is essential to develop high‐performance optoelectronic neuromorphic electronics with broadband response, low power consumption, and fast response speed. Among these, optoelectronic synaptic transistors have emerged as promising candidates for constructing neuromorphic visual systems. In this work, flexible printed broadband (from 275 to 1050 nm) optoelectronic carbon nanotube synaptic transistors with good stability, high response speed (3.14 ms), and low‐power consumption (as low as 0.1 fJ per event with the 1050 nm pulse illumination) using PbS quantum dots (QDs) modified semiconducting single‐walled carbon nanotubes (sc‐SWCNTs) as active layers are developed. In response to optical pulses within the ultraviolet to near‐infrared wavelength range, the optoelectronic neuromorphic devices exhibit excitatory postsynaptic current, paired‐pulse facilitation, and a transition from short‐term plasticity to long‐term plasticity, and other optical synaptic behaviors. Furthermore, a simplified neural morphology visual array is developed to simulate integrated functions such as image perception, memory, and preprocessing. More importantly, it can also emulate other complicated bionic functions, such as the infrared perception of salmon eyes and the warning behavior of reindeer in different environments. This work holds immense significance in advancing the development of artificial neural visual systems.

show abstract

Configurable NbO_x Memristors as Artificial Synapses or Neurons Achieved by Regulating the Forming Compliance Current for the Spiking Neural Network

Cited by 11 publications

References 43 publications

Resistive Switching Devices for Neuromorphic Computing: From Foundations to Chip Level Innovations

Resistive Switching Devices for Neuromorphic Computing: From Foundations to Chip Level Innovations

Secondary Order RC Sensor Neuron Circuit for Direct Input Encoding in Spiking Neural Network

Flexible Printed Ultraviolet‐to‐Near‐Infrared Broadband Optoelectronic Carbon Nanotube Synaptic Transistors for Fast and Energy‐Efficient Neuromorphic Vision Systems

Contact Info

Product

Resources

About

Configurable NbOx Memristors as Artificial Synapses or Neurons Achieved by Regulating the Forming Compliance Current for the Spiking Neural Network

Cited by 11 publications

References 43 publications

Resistive Switching Devices for Neuromorphic Computing: From Foundations to Chip Level Innovations

Resistive Switching Devices for Neuromorphic Computing: From Foundations to Chip Level Innovations

Secondary Order RC Sensor Neuron Circuit for Direct Input Encoding in Spiking Neural Network

Flexible Printed Ultraviolet‐to‐Near‐Infrared Broadband Optoelectronic Carbon Nanotube Synaptic Transistors for Fast and Energy‐Efficient Neuromorphic Vision Systems

Contact Info

Product

Resources

About

Configurable NbO_x Memristors as Artificial Synapses or Neurons Achieved by Regulating the Forming Compliance Current for the Spiking Neural Network