Redox memristors with volatile threshold switching behavior for neuromorphic computing

Wang, Yuhao; Gong, Tiancheng; Ding, Yaxin; Li, Yang; Wang, Wei; Chen, Ziang; Du, Nan; Covi, Erika; Farronato, Matteo; Ielmini, Daniele; Zhang, Xu-Meng; Luo, Qing

doi:10.1016/j.jnlest.2022.100177

Cited by 7 publications

(5 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advent of emerging technologies and the research in volatile resistive memory devices offer a promising frontier for the area-efficient development of adaptive neurons on analog hardware 86 , 87 . This approach can obviate the need for large capacitors, allowing the adjustment of time constants based on programming current, thus playing a crucial role in tuning the adaptation time constant for RSNNs.…”

Section: Discussion and Road Aheadmentioning

confidence: 99%

“…However, asynchronous processing can potentially lead to further energy savings and computational advantages in SNNs. Future work may explore the integration of asynchronous mechanisms within these models to better align with biological neural systems The advent of emerging technologies and the research in volatile resistive memory devices offer a promising frontier for the area-efficient development of adaptive neurons on analog hardware 86,87 . This approach can obviate the need for large capacitors, allowing the adjustment of time constants based on programming current, thus playing a crucial role in tuning the adaptation time constant for RSNNs.…”

Section: Challenges and Roadmapmentioning

confidence: 99%

See 1 more Smart Citation

Spike frequency adaptation: bridging neural models and neuromorphic applications

Ganguly,

Bezugam,

Abs

et al. 2024

Commun Eng

View full text Add to dashboard Cite

The human brain’s unparalleled efficiency in executing complex cognitive tasks stems from neurons communicating via short, intermittent bursts or spikes. This has inspired Spiking Neural Networks (SNNs), now incorporating neuron models with spike frequency adaptation (SFA). SFA adjusts these spikes’ frequency based on recent neuronal activity, much like an athlete’s varying sprint speed. SNNs with SFA demonstrate improved computational performance and energy efficiency. This review examines various adaptive neuron models in computational neuroscience, highlighting their relevance in artificial intelligence and hardware integration. It also discusses the challenges and potential of these models in driving the development of energy-efficient neuromorphic systems.

show abstract

Section: Discussion and Road Aheadmentioning

confidence: 99%

Section: Challenges and Roadmapmentioning

confidence: 99%

Spike frequency adaptation: bridging neural models and neuromorphic applications

Ganguly,

Bezugam,

Abs

et al. 2024

Commun Eng

View full text Add to dashboard Cite

show abstract

“…Additionally, these devices can generate spike signal outputs and operate under the principles of spike-based computing, a method that the brain uses to process information, with remarkable energy efficiency. [97,98] In this regard, memristor-based artificial neuron devices present the possibility of developing power-efficient neuromorphic systems that can perform complex computations with less energy. As the implementation of such power-efficient computing systems requires careful consideration of several factors such as device design, material selection, and integration of devices into larger systems, we will examine the current state of the technology, remaining challenges, and potential solutions to overcome these challenges to realize power-efficient spike-based neuromorphic computing.…”

Section: Low Energy Consumptionmentioning

confidence: 99%

“…Research on using Mott transition characteristics in artificial neuron devices is actively being conducted. As MIT‐based neuron devices switch between the insulating and metallic phases because of the atomic rearrangement, they have higher switching speeds owing to the short‐range atomic rearrangement (≈ns), [ 98,159 ] making them suitable for high‐frequency spike generators. Owing to their high switching speeds, which follow the increment in charging speed, they show linear increases in spikes with the increase in the input current amplitude.…”

Section: Memristor‐based Artificial Sensory Systemmentioning

confidence: 99%

Artificial sensory system based on memristive devices

Kwon,

Kim,

Kim

et al. 2023

Exploration

View full text Add to dashboard Cite

In the biological nervous system, the integration and cooperation of parallel system of receptors, neurons, and synapses allow efficient detection and processing of intricate and disordered external information. Such systems acquire and process environmental data in real‐time, efficiently handling complex tasks with minimal energy consumption. Memristors can mimic typical biological receptors, neurons, and synapses by implementing key features of neuronal signal‐processing functions such as selective adaption in receptors, leaky integrate‐and‐fire in neurons, and synaptic plasticity in synapses. External stimuli are sensitively detected and filtered by “artificial receptors,” encoded into spike signals via “artificial neurons,” and integrated and stored through “artificial synapses.” The high operational speed, low power consumption, and superior scalability of memristive devices make their integration with high‐performance sensors a promising approach for creating integrated artificial sensory systems. These integrated systems can extract useful data from a large volume of raw data, facilitating real‐time detection and processing of environmental information. This review explores the recent advances in memristor‐based artificial sensory systems. The authors begin with the requirements of artificial sensory elements and then present an in‐depth review of such elements demonstrated by memristive devices. Finally, the major challenges and opportunities in the development of memristor‐based artificial sensory systems are discussed.

show abstract

“…The relevance of memristive materials for neuromorphic engineering applications has been recently acknowledged and is developing fast [17][18][19]. There are various proposals for the implementation of spiking neurons based on memristive materials.…”

Section: Introductionmentioning

confidence: 99%

Bursting dynamics in a spiking neuron with a memristive voltage-gated channel

Wu,

Wang,

Schneegans

et al. 2023

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

We introduce a voltage-gated conductance model for an artificial neuron that exhibits tonic, fast, and two types of intrinsic burst spiking. The spike generation is achieved with a single voltage-gated channel that exploits the conductance commutation properties of a two-terminal memristive device. Our circuit implementation is of unprecedented simplicity, using just four electronic components, all conventional, cheap and out-of-the-shelf. Our bursting neuron is a two-compartment model, similar to the Pinsky–Rinzel model. We obtain the full phase diagram and discuss the origin of the different regions. We find that the spike traces of the model bare striking similarity to experimental biological neuronal recordings. Our work may open a new way to investigate neural pathologies, such as epilepsy and Parkinson’s disease, from the study of the phase diagram and the transitions between spiking states of physical neuron models.

show abstract

Redox memristors with volatile threshold switching behavior for neuromorphic computing

Cited by 7 publications

References 61 publications

Spike frequency adaptation: bridging neural models and neuromorphic applications

Spike frequency adaptation: bridging neural models and neuromorphic applications

Artificial sensory system based on memristive devices

Bursting dynamics in a spiking neuron with a memristive voltage-gated channel

Contact Info

Product

Resources

About