The Experts below are selected from a list of 8925 Experts worldwide ranked by ideXlab platform
Lu Liu - One of the best experts on this subject based on the ideXlab platform.
-
multilayer rtd memristor based cellular neural networks for color image processing
Neurocomputing, 2015Co-Authors: Gang Feng, Shukai Duan, Lu LiuAbstract:Multilayer cellular neural networks (CNNs) with multiple state variables in each cell associated with multiple dynamic rules are believed to possess more powerful data computing and signal processing capabilities than single-layer CNNs and are specially suitable for solving complex problems. However, at present, their large scale integrated hardware implementation is still quite challenging based on traditional CMOS-based technology due to high circuity complexity and their applications are thus limited in practice. In this paper, a novel compact multilayer CNN model based on nanometer scale resonant tunneling diodes (RTDs) and memristors is presented. More specifically, in this model, one multilayer CNN cell consists of several sub-cells located in different layers. The resonant tunneling diode with quantum tunneling induced nonlinearity and uniquely folded current-voltage characteristics is used to implement the compact and high-speed cell via replacing the original linear resistor and removing the output function of conventional CNN cells. Furthermore, the interactions between these cells are determined by a pair of multi-dimensional cloning Templates. And a compact synaptic circuit based on memristors is designed to realize the cloning Template Parameter (weight strength) and the multiplication (weighting) operation, by leveraging its nonvolatility, good scalability, and variable conductance. The combination of these desirable elements equips the proposed multilayer CNN with advantages of powerful processing capability as well as high compactness, versatility, and possibility of very large scale integration (VLSI) circuit implementations. Finally, the performance of the proposed multilayer CNN is validated by five illustrative examples in color image processing with each layer dealing with each primary color (red, green or blue) plane. Nanoscale RTDs and memristors improve the circuit integration and resolution.Multilayer architecture provides more powerful processing ability and versatility.The memristor with thresholds promises effective writing and undisturbed reading.
Gang Feng - One of the best experts on this subject based on the ideXlab platform.
-
multilayer rtd memristor based cellular neural networks for color image processing
Neurocomputing, 2015Co-Authors: Gang Feng, Shukai Duan, Lu LiuAbstract:Multilayer cellular neural networks (CNNs) with multiple state variables in each cell associated with multiple dynamic rules are believed to possess more powerful data computing and signal processing capabilities than single-layer CNNs and are specially suitable for solving complex problems. However, at present, their large scale integrated hardware implementation is still quite challenging based on traditional CMOS-based technology due to high circuity complexity and their applications are thus limited in practice. In this paper, a novel compact multilayer CNN model based on nanometer scale resonant tunneling diodes (RTDs) and memristors is presented. More specifically, in this model, one multilayer CNN cell consists of several sub-cells located in different layers. The resonant tunneling diode with quantum tunneling induced nonlinearity and uniquely folded current-voltage characteristics is used to implement the compact and high-speed cell via replacing the original linear resistor and removing the output function of conventional CNN cells. Furthermore, the interactions between these cells are determined by a pair of multi-dimensional cloning Templates. And a compact synaptic circuit based on memristors is designed to realize the cloning Template Parameter (weight strength) and the multiplication (weighting) operation, by leveraging its nonvolatility, good scalability, and variable conductance. The combination of these desirable elements equips the proposed multilayer CNN with advantages of powerful processing capability as well as high compactness, versatility, and possibility of very large scale integration (VLSI) circuit implementations. Finally, the performance of the proposed multilayer CNN is validated by five illustrative examples in color image processing with each layer dealing with each primary color (red, green or blue) plane. Nanoscale RTDs and memristors improve the circuit integration and resolution.Multilayer architecture provides more powerful processing ability and versatility.The memristor with thresholds promises effective writing and undisturbed reading.
Shukai Duan - One of the best experts on this subject based on the ideXlab platform.
-
multilayer rtd memristor based cellular neural networks for color image processing
Neurocomputing, 2015Co-Authors: Gang Feng, Shukai Duan, Lu LiuAbstract:Multilayer cellular neural networks (CNNs) with multiple state variables in each cell associated with multiple dynamic rules are believed to possess more powerful data computing and signal processing capabilities than single-layer CNNs and are specially suitable for solving complex problems. However, at present, their large scale integrated hardware implementation is still quite challenging based on traditional CMOS-based technology due to high circuity complexity and their applications are thus limited in practice. In this paper, a novel compact multilayer CNN model based on nanometer scale resonant tunneling diodes (RTDs) and memristors is presented. More specifically, in this model, one multilayer CNN cell consists of several sub-cells located in different layers. The resonant tunneling diode with quantum tunneling induced nonlinearity and uniquely folded current-voltage characteristics is used to implement the compact and high-speed cell via replacing the original linear resistor and removing the output function of conventional CNN cells. Furthermore, the interactions between these cells are determined by a pair of multi-dimensional cloning Templates. And a compact synaptic circuit based on memristors is designed to realize the cloning Template Parameter (weight strength) and the multiplication (weighting) operation, by leveraging its nonvolatility, good scalability, and variable conductance. The combination of these desirable elements equips the proposed multilayer CNN with advantages of powerful processing capability as well as high compactness, versatility, and possibility of very large scale integration (VLSI) circuit implementations. Finally, the performance of the proposed multilayer CNN is validated by five illustrative examples in color image processing with each layer dealing with each primary color (red, green or blue) plane. Nanoscale RTDs and memristors improve the circuit integration and resolution.Multilayer architecture provides more powerful processing ability and versatility.The memristor with thresholds promises effective writing and undisturbed reading.
Olivier Veziant - One of the best experts on this subject based on the ideXlab platform.
-
New contour reconstruction technique in Template Parameter space and associated placement
Classical and Quantum Gravity, 2003Co-Authors: F. Beauville, D. Buskulic, R. Flaminio, F. Marion, B. Mours, E. Tournefier, D. Verkindt, Louis Massonet, Julien Ramonet, Olivier VeziantAbstract:The generation of a grid of Templates and their placement in the Parameter space is one of the problems that has to be addressed in the search for binary system coalescences detectable in interferometric gravitational wave detectors. We present a technique that computes the closed contour of equal match values around a point in Parameter space and a first test of a Template placement algorithm using these contours. This algorithm could be used to pave the Parameter space. First results about the algorithm's covering efficiency are also presented.
Lijing Yan - One of the best experts on this subject based on the ideXlab platform.
-
proceedings paper Template Parameter optimization of vertical drying system for corn ears based on bp neural network
2020Co-Authors: Qiang Fei, Lijing YanAbstract:In the northwest of China, corns are harvested during late autumn. The cold weather determines that corn ears must be quickly dried before stored. Vertical drying system, whose performance Parameters are drying effectiveness, moisture ratio and drying uniformity, is extensively used there. In this paper, type 5HZL-1200 vertical drying system was selected as study object. In order to obtain the optimum results and save experiment costs, a mathematical model of nonlinear system with multiple inputs and outputs was established and trained based on BP neural networks. Simulation results were compared with experimental data and showed little difference, which indicates that Parameters and performance of vertical drying system for corn ears can be accurately simulated and predicted. Aiming at the optimal combination of influence factors, according with main objects method in mathematical programming, single Parameter was optimized with MATLAB optimization tool, respectively, and then other objects were added to obtain the optimal combination. All the processes were recurred and verified by genetic algorithm. The operation result shows that there is little difference of dependent variables between the two optimization methods. Besides, the application of MATLAB optimization tool increases the drying effectiveness by 0.97–1.70%. The application of MATLAB toolkit based on BP neural network and genetic algorithm in modeling and optimization provides a new method to determine the Parameters of vertical drying system for corn ears.
