A5090042508- Advanced Memory and Neural Computing
- Ferroelectric and Negative Capacitance Devices
- Neural Networks and Reservoir Computing
- Neural dynamics and brain function
- Neuroscience and Neural Engineering
- Semiconductor materials and devices
- Photoreceptor and optogenetics research
- Neural Networks and Applications
- Machine Learning and ELM
- Transition Metal Oxide Nanomaterials
- CCD and CMOS Imaging Sensors
- MicroRNA in disease regulation
- Neurotransmitter Receptor Influence on Behavior
- Advancements in Semiconductor Devices and Circuit Design
- Electronic and Structural Properties of Oxides
- Analytical Chemistry and Sensors
- 2D Materials and Applications
- Phase-change materials and chalcogenides
- Air Quality Monitoring and Forecasting
- Perovskite Materials and Applications
- Conducting polymers and applications
- Air Quality and Health Impacts
- Concrete and Cement Materials Research
- GaN-based semiconductor devices and materials
- Integrated Circuits and Semiconductor Failure Analysis
Southern University of Science and Technology
2024-2025
Hong Kong Science and Technology Parks Corporation
2022-2025
Beijing Academy of Artificial Intelligence
2025
University of Hong Kong
2020-2025
Shandong University
2023-2025
Wuhan Institute of Technology
2022-2025
University of Southern California
2024
Shanghai East Hospital
2018-2024
Zhejiang University
2024
Chinese University of Hong Kong
2024
Memristors with tunable resistance states are emerging building blocks of artificial neural networks. However, in situ learning on a large-scale multiple-layer memristor network has yet to be demonstrated because challenges device property engineering and circuit integration. Here we monolithically integrate hafnium oxide-based memristors foundry-made transistor array into network. We experimentally demonstrate capability achieve competitive classification accuracy standard machine dataset,...
Neuromorphic computers could overcome efficiency bottlenecks inherent to conventional computing through parallel programming and readout of artificial neural network weights in a crossbar memory array. However, selective linear weight updates <10-nanoampere read currents are required for learning that surpasses efficiency. We introduce an ionic floating-gate array based on polymer redox transistor connected conductive-bridge (CBM). Selective is executed by overcoming the bridging threshold...
Abstract A neuromorphic computing system may be able to learn and perform a task on its own by interacting with surroundings. Combining such chip complementary metal–oxide–semiconductor (CMOS)‐based processors can potentially solve variety of problems being faced today's artificial intelligence (AI) systems. Although various architectures purely based CMOS are designed maximize the efficiency AI‐based applications, most fundamental operations including matrix multiplication convolution...
A nociceptor is a critical and special receptor of sensory neuron that able to detect noxious stimulus provide rapid warning the central nervous system start motor response in human body humanoid robotics. It differs from other common receptors with its key features functions, including "no adaptation" "sensitization" phenomena. In this study, we propose experimentally demonstrate an artificial based on diffusive memristor dynamics for first time. Using nociceptor, further built alarm...
The intrinsic variability of switching behavior in memristors has been a major obstacle to their adoption as the next generation universal memory. On other hand, this natural stochasticity can be valuable for hardware security applications. Here we propose and demonstrate novel true random number generator utilizing stochastic delay time threshold Ag:SiO2 diffusive memristor, which exhibits evident advantages scalability, circuit complexity, power consumption. bits generated by memristor...
A novel Ag/oxide-based threshold switching device with attractive features including ≈1010 nonlinearity is developed. High-resolution transmission electron microscopic analysis of the nanoscale crosspoint suggests that elongation an Ag nanoparticle under voltage bias followed by spontaneous reformation a more spherical shape after power off responsible for observed switching.
Abstract Neuromorphic computing based on spikes offers great potential in highly efficient paradigms. Recently, several hardware implementations of spiking neural networks traditional complementary metal-oxide semiconductor technology or memristors have been developed. However, an interface (called afferent nerve biology) with the environment, which converts analog signal from sensors into networks, is yet to be demonstrated. Here we propose and experimentally demonstrate artificial reliable...
Abstract Threshold switches with Ag or Cu active metal species are volatile memristors (also termed diffusive memristors) featuring spontaneous rupture of conduction channels. The temporal dynamics the conductance evolution is closely related to electrochemical and metals which could be modulated by electric field strength, biasing duration, temperature, so on. Microscopic pictures electron microscopy quantitative thermodynamics modeling examined give insights into underlying physics...
Early processing of visual information takes place in the human retina. Mimicking neurobiological structures and functionalities retina provides a promising pathway to achieving vision sensor with highly efficient image processing. Here, we demonstrate prototype that operates via gate-tunable positive negative photoresponses van der Waals (vdW) vertical heterostructures. The emulates not only bipolar cells photoreceptors but also unique connectivity between photoreceptors. By tuning gate...
This article provides a review of current development and challenges in brain-inspired computing with memristors. We the mechanisms various memristive devices that can mimic synaptic neuronal functionalities survey progress spiking artificial neural networks. Different architectures are compared, including networks, fully connected convolutional Hopfield recurrent Challenges strategies for nanoelectronic systems, device variations, training, testing algorithms, also discussed.
High dimensionality and fading memory for in-sensor reservoir computing are achieved via two-dimensional memristors.
Experimental demonstration of resistive neural networks has been the recent focus hardware implementation neuromorphic computing. Capacitive networks, which call for novel building blocks, provide an alternative physical embodiment featuring a lower static power and better emulation functionalities. Here, we develop neuro-transistors by integrating dynamic pseudo-memcapacitors as gates transistors to produce electronic analogs soma axon neuron, with "leaky integrate-and-fire" dynamics...
Abstract Memristive devices are promising candidates for the next generation non-volatile memory and neuromorphic computing. It has been widely accepted that motion of oxygen anions leads to resistance changes valence-change-memory (VCM) type materials. Only very recently it was speculated metal cations could also play an important role, but no direct physical characterizations have reported yet. Here we report a Ta/HfO 2 /Pt memristor with fast switching speed, record high endurance (120...
Reservoir computing (RC) is a framework that can extract features from temporal input into higher‐dimension feature space. The reservoir followed by readout layer analyze the extracted to accomplish tasks such as inference and classification. RC systems inherently exhibit an advantage, since training only performed at layer, therefore they are able compute complicated data with low cost. Herein, physical system using diffusive memristor‐based drift experimentally implemented. rich nonlinear...