Low-power and low-variability artificial neuronal devices are highly desired for high-performance neuromorphic computing.In this paper,an oscillation neuron based on a low-variability Ag nanodots(NDs)threshold switchi...Low-power and low-variability artificial neuronal devices are highly desired for high-performance neuromorphic computing.In this paper,an oscillation neuron based on a low-variability Ag nanodots(NDs)threshold switching(TS)device with low operation voltage,large on/off ratio and high uniformity is presented.Measurement results indicate that this neuron demonstrates self-oscillation behavior under applied voltages as low as 1 V.The oscillation frequency increases with the applied voltage pulse amplitude and decreases with the load resistance.It can then be used to evaluate the resistive random-access memory(RRAM)synaptic weights accurately when the oscillation neuron is connected to the output of the RRAM crossbar array for neuromorphic computing.Meanwhile,simulation results show that a large RRAM crossbar array(>128×128)can be supported by our oscillation neuron owing to the high on/off ratio(>10^(8))of Ag NDs TS device.Moreover,the high uniformity of the Ag NDs TS device helps improve the distribution of the output frequency and suppress the degradation of neural network recognition accuracy(<1%).Therefore,the developed oscillation neuron based on the Ag NDs TS device shows great potential for future neuromorphic computing applications.展开更多
Aligned arrays of semiconducting carbon nanotubes(s-CNTs)with high homogenous density and orientation are urgently needed for high-performance carbon-based electronics.Herein,a length-controlled approach using combine...Aligned arrays of semiconducting carbon nanotubes(s-CNTs)with high homogenous density and orientation are urgently needed for high-performance carbon-based electronics.Herein,a length-controlled approach using combined technologies was developed to regulate the s-CNT length and reduce the length distribution.The impact of different lengths and length distributions was studied during aligned self-assembly on a liquid–liquid confined interface was investigated.The results show that short s-CNTs with a narrow distribution have the best alignment uniformity over the large scale.The optimized and aligned s-CNT array can reach a density as high as 100 CNTs·μm−1 on a 4-inch wafer.The field-effect transistor(FET)performance of these optimized s-CNT arrays was 64%higher than arrays without length-control.This study clarified that rational control of s-CNTs with desired length and length distribution on the aligned self-assembly process within the liquid–liquid confined interface.The results illustrate a solid foundation for the application of emerging carbon-based electronics.展开更多
The rapid growth of the Internet of Things(IoTs)has resulted in an explosive increase in data,and thus has raised new challenges for data processing units.Edge computing,which settles signal processing and computing t...The rapid growth of the Internet of Things(IoTs)has resulted in an explosive increase in data,and thus has raised new challenges for data processing units.Edge computing,which settles signal processing and computing tasks at the edge of networks rather than uploading data to the cloud,can reduce the amount of data for transmission and is a promising solution to address the challenges.One of the potential candidates for edge computing is a memristor,an emerging nonvolatile memory device that has the capability of in-memory computing.In this article,from the perspective of edge computing,we review recent progress on memristor-based signal processing methods,especially on the aspects of signal preprocessing and feature extraction.Then,we describe memristor-based signal classification and regression,and end-to-end signal processing.In all these applications,memristors serve as critical accelerators to greatly improve the overall system performance,such as power efficiency and processing speed.Finally,we discuss existing challenges and future outlooks for memristor-based signal processing systems.展开更多
Photodetectors and optoelectronic synapses are vital for construction of artificial visual perception system.However,the hardware implementations of optoelectronic-neuromorphic devices based on conventional architectu...Photodetectors and optoelectronic synapses are vital for construction of artificial visual perception system.However,the hardware implementations of optoelectronic-neuromorphic devices based on conventional architecture usually suffer from poor scalability,light response range,and limited functionalities.Here,large-scale flexible monolayer MoS_(2)devices integrating photodetectors and optoelectronic synapses over the entire visible spectrum in one device have been realized,which can be used in photodetection,optical communication,artificial visual perception system,and optical artificial neural network.By modulating gate voltages,we enable MoS_(2)-based devices to be photodetectors and also optoelectronic synapses.Importantly,the MoS_(2)-based optoelectronic synapses could implement many synaptic functions and neuromorphic characteristics,such as short-term memory(STM),long-term memory(LTM),paired-pulse facilitation(PPF),long-term potentiation(LTP)/long-term depression(LTD),and“learning-experience”behavior.Furthermore,an associative learning behavior(the classical conditioning Pavlov’s dog experiment)was emulated using paired stimulation of optical and voltage pulses.These results facilitate the development of MoS_(2)-based multifunctional optoelectronic devices with a simple device structure,showing great potential for photodetection,optoelectronic neuromorphic computing,human visual systems mimicking,as well as wearable and implantable electronics.展开更多
Mathematical morphology operations are widely used in image processing such as defect analysis in semiconductor manufacturing and medical image analysis.These data-intensive applications have high requirements during ...Mathematical morphology operations are widely used in image processing such as defect analysis in semiconductor manufacturing and medical image analysis.These data-intensive applications have high requirements during hardware implementation that are challenging for conventional hardware platforms such as central processing units(CPUs)and graphics processing units(GPUs).Computation-in-memory(CIM)provides a possible solution for highly efficient morphology operations.In this study,we demonstrate the application of morphology operation with a novel memristor-based auto-detection architecture and demonstrate non-neuromoq)hic computation on a multi-array-based memristor system.Pixel-by-pixel logic computations with low parallelism are converted to parallel operations using memristors.Moreover,hardware-implemented computer-integrated manufacturing was used to experimentally demonstrate typical defect detection tasks in integrated circuit(IC)manufacturing and medical image analysis.In addition,we developed a new implementation scheme employing a four-layer network to realize small-object detection with high parallelism.The system benchmark based on the hardware measurement results showed significant improvement in the energy efficiency by approximately 358 times and 32 times more than when a CPU and GPU were employed,respectively,exhibiting the advantage of the proposed memristor-based morphology operation.展开更多
基金supported in part by China Key Research and Development Program(2016YFA0201800)the National Natural Science Foundation of China(91964104,61974081)。
文摘Low-power and low-variability artificial neuronal devices are highly desired for high-performance neuromorphic computing.In this paper,an oscillation neuron based on a low-variability Ag nanodots(NDs)threshold switching(TS)device with low operation voltage,large on/off ratio and high uniformity is presented.Measurement results indicate that this neuron demonstrates self-oscillation behavior under applied voltages as low as 1 V.The oscillation frequency increases with the applied voltage pulse amplitude and decreases with the load resistance.It can then be used to evaluate the resistive random-access memory(RRAM)synaptic weights accurately when the oscillation neuron is connected to the output of the RRAM crossbar array for neuromorphic computing.Meanwhile,simulation results show that a large RRAM crossbar array(>128×128)can be supported by our oscillation neuron owing to the high on/off ratio(>10^(8))of Ag NDs TS device.Moreover,the high uniformity of the Ag NDs TS device helps improve the distribution of the output frequency and suppress the degradation of neural network recognition accuracy(<1%).Therefore,the developed oscillation neuron based on the Ag NDs TS device shows great potential for future neuromorphic computing applications.
基金This work was supported by National Key Research and Development Program of China(No.2020YFA0714700)National Natural Science Foundation of China(Nos.22075312 and 21773292)Key-Area Research and Development Program of Guangdong Province(No.2019B010934001).
文摘Aligned arrays of semiconducting carbon nanotubes(s-CNTs)with high homogenous density and orientation are urgently needed for high-performance carbon-based electronics.Herein,a length-controlled approach using combined technologies was developed to regulate the s-CNT length and reduce the length distribution.The impact of different lengths and length distributions was studied during aligned self-assembly on a liquid–liquid confined interface was investigated.The results show that short s-CNTs with a narrow distribution have the best alignment uniformity over the large scale.The optimized and aligned s-CNT array can reach a density as high as 100 CNTs·μm−1 on a 4-inch wafer.The field-effect transistor(FET)performance of these optimized s-CNT arrays was 64%higher than arrays without length-control.This study clarified that rational control of s-CNTs with desired length and length distribution on the aligned self-assembly process within the liquid–liquid confined interface.The results illustrate a solid foundation for the application of emerging carbon-based electronics.
基金supported in part by the National Science and Technology Major Project of China(No.2017ZX02315001-005)the National Natural Science Foundation of China(Nos.91964104 and 61974081)。
文摘The rapid growth of the Internet of Things(IoTs)has resulted in an explosive increase in data,and thus has raised new challenges for data processing units.Edge computing,which settles signal processing and computing tasks at the edge of networks rather than uploading data to the cloud,can reduce the amount of data for transmission and is a promising solution to address the challenges.One of the potential candidates for edge computing is a memristor,an emerging nonvolatile memory device that has the capability of in-memory computing.In this article,from the perspective of edge computing,we review recent progress on memristor-based signal processing methods,especially on the aspects of signal preprocessing and feature extraction.Then,we describe memristor-based signal classification and regression,and end-to-end signal processing.In all these applications,memristors serve as critical accelerators to greatly improve the overall system performance,such as power efficiency and processing speed.Finally,we discuss existing challenges and future outlooks for memristor-based signal processing systems.
基金supports from the KeyArea Research and Development Program of Guangdong Province(No.2020B0101340001)the National Natural Science Foundation of China(Nos.61888102,11834017,51901025,and 12074412)+1 种基金the Strategic Priority Research Program of Chinese Academy of Sciences(CAS)(No.XDB30000000)Postdoctoral Innovative Talent Support Program(No.BX2021351)。
文摘Photodetectors and optoelectronic synapses are vital for construction of artificial visual perception system.However,the hardware implementations of optoelectronic-neuromorphic devices based on conventional architecture usually suffer from poor scalability,light response range,and limited functionalities.Here,large-scale flexible monolayer MoS_(2)devices integrating photodetectors and optoelectronic synapses over the entire visible spectrum in one device have been realized,which can be used in photodetection,optical communication,artificial visual perception system,and optical artificial neural network.By modulating gate voltages,we enable MoS_(2)-based devices to be photodetectors and also optoelectronic synapses.Importantly,the MoS_(2)-based optoelectronic synapses could implement many synaptic functions and neuromorphic characteristics,such as short-term memory(STM),long-term memory(LTM),paired-pulse facilitation(PPF),long-term potentiation(LTP)/long-term depression(LTD),and“learning-experience”behavior.Furthermore,an associative learning behavior(the classical conditioning Pavlov’s dog experiment)was emulated using paired stimulation of optical and voltage pulses.These results facilitate the development of MoS_(2)-based multifunctional optoelectronic devices with a simple device structure,showing great potential for photodetection,optoelectronic neuromorphic computing,human visual systems mimicking,as well as wearable and implantable electronics.
基金the National Natural Science Foundation of China(Grants No.92064001,61851404,and 61874169)the IoT Intelligent Microsystem Center of Tsinghua University-China Mobile Joint Research Institute.
文摘Mathematical morphology operations are widely used in image processing such as defect analysis in semiconductor manufacturing and medical image analysis.These data-intensive applications have high requirements during hardware implementation that are challenging for conventional hardware platforms such as central processing units(CPUs)and graphics processing units(GPUs).Computation-in-memory(CIM)provides a possible solution for highly efficient morphology operations.In this study,we demonstrate the application of morphology operation with a novel memristor-based auto-detection architecture and demonstrate non-neuromoq)hic computation on a multi-array-based memristor system.Pixel-by-pixel logic computations with low parallelism are converted to parallel operations using memristors.Moreover,hardware-implemented computer-integrated manufacturing was used to experimentally demonstrate typical defect detection tasks in integrated circuit(IC)manufacturing and medical image analysis.In addition,we developed a new implementation scheme employing a four-layer network to realize small-object detection with high parallelism.The system benchmark based on the hardware measurement results showed significant improvement in the energy efficiency by approximately 358 times and 32 times more than when a CPU and GPU were employed,respectively,exhibiting the advantage of the proposed memristor-based morphology operation.