In order to study the problem of intelligent information processing in new types of imaging fuze, the method of extracting the invariance features of target images is adopted, and radial basis function neural network ...In order to study the problem of intelligent information processing in new types of imaging fuze, the method of extracting the invariance features of target images is adopted, and radial basis function neural network is used to recognize targets. Owing to its ability of parallel processing, its robustness and generalization, the method can realize the recognition of the conditions of missile-target encounters, and meet the requirements of real-time recognition in the imaging fuze. It is shown that based on artificial neural network target recognition and burst point control are feasible.展开更多
In recent years,space-division multiplexing(SDM)technology,which involves transmitting data information on multiple parallel channels for efficient capacity scaling,has been widely used in fiber and free-space optical...In recent years,space-division multiplexing(SDM)technology,which involves transmitting data information on multiple parallel channels for efficient capacity scaling,has been widely used in fiber and free-space optical communication sys-tems.To enable flexible data management and cope with the mixing between different channels,the integrated reconfig-urable optical processor is used for optical switching and mitigating the channel crosstalk.However,efficient online train-ing becomes intricate and challenging,particularly when dealing with a significant number of channels.Here we use the stochastic parallel gradient descent(SPGD)algorithm to configure the integrated optical processor,which has less com-putation than the traditional gradient descent(GD)algorithm.We design and fabricate a 6×6 on-chip optical processor on silicon platform to implement optical switching and descrambling assisted by the online training with the SPDG algorithm.Moreover,we apply the on-chip processor configured by the SPGD algorithm to optical communications for optical switching and efficiently mitigating the channel crosstalk in SDM systems.In comparison with the traditional GD al-gorithm,it is found that the SPGD algorithm features better performance especially when the scale of matrix is large,which means it has the potential to optimize large-scale optical matrix computation acceleration chips.展开更多
Temporal information processing in the range of tens to hundreds of milliseconds is critical in many forms of sensory and motor tasks. However, little has been known about the neural mechanisms of temporal information...Temporal information processing in the range of tens to hundreds of milliseconds is critical in many forms of sensory and motor tasks. However, little has been known about the neural mechanisms of temporal information processing. Experimental observations indicate that sensory neurons of the nervous system do not show selective response to temporal properties of external stimuli. On the other hand, temporal selective neurons in the cortex have been reported in many species. Thus, processes which realize the temporal-to-spatial transformation of neuronal activities might be required for temporal information processing. In the present study, we propose a computational model to explore possible roles of electrical synapses in processing the duration of external stimuli. Firstly, we construct a small-scale network with neurons interconnected by electrical synapses in addition to chemical synapses. Basic properties of this small-scale neural network in processing duration information are analyzed. Secondly, a large-scale neural network which is more biologically realistic is further explored. Our results suggest that neural networks with electrical synapses functioning together with chemical synapses can effectively work for the temporal-to-spatial transformation of neuronal activities, and the spatially distributed sequential neural activities can potentially represent temporal information.展开更多
At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production ...At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production environments,there are a large number of KGs with a small number of entities and relations,which are called sparse KGs.Limited by the performance of knowledge extraction methods or some other reasons(some common-sense information does not appear in the natural corpus),the relation between entities is often incomplete.To solve this problem,a method of the graph neural network and information enhancement is proposed.The improved method increases the mean reciprocal rank(MRR)and Hit@3 by 1.6%and 1.7%,respectively,when the sparsity of the FB15K-237 dataset is 10%.When the sparsity is 50%,the evaluation indexes MRR and Hit@10 are increased by 0.8%and 1.8%,respectively.展开更多
In this study,we developed a system based on deep space–time neural networks for gesture recognition.When users change or the number of gesture categories increases,the accuracy of gesture recognition decreases consi...In this study,we developed a system based on deep space–time neural networks for gesture recognition.When users change or the number of gesture categories increases,the accuracy of gesture recognition decreases considerably because most gesture recognition systems cannot accommodate both user differentiation and gesture diversity.To overcome the limitations of existing methods,we designed a onedimensional parallel long short-term memory–fully convolutional network(LSTM–FCN)model to extract gesture features of different dimensions.LSTM can learn complex time dynamic information,whereas FCN can predict gestures efficiently by extracting the deep,abstract features of gestures in the spatial dimension.In the experiment,50 types of gestures of five users were collected and evaluated.The experimental results demonstrate the effectiveness of this system and robustness to various gestures and individual changes.Statistical analysis of the recognition results indicated that an average accuracy of approximately 98.9% was achieved.展开更多
Radial basis function neural network(RBFNN) is an effective algorithm in nonlinear system identification. How to properly adjust the structure and parameters of RBFNN is quite challenging. To solve this problem, a dis...Radial basis function neural network(RBFNN) is an effective algorithm in nonlinear system identification. How to properly adjust the structure and parameters of RBFNN is quite challenging. To solve this problem, a distance concentration immune algorithm(DCIA) is proposed to self-organize the structure and parameters of the RBFNN in this paper. First, the distance concentration algorithm, which increases the diversity of antibodies, is used to find the global optimal solution. Secondly,the information processing strength(IPS) algorithm is used to avoid the instability that is caused by the hidden layer with neurons split or deleted randomly. However, to improve the forecasting accuracy and reduce the computation time, a sample with the most frequent occurrence of maximum error is proposed to regulate the parameters of the new neuron. In addition, the convergence proof of a self-organizing RBF neural network based on distance concentration immune algorithm(DCIA-SORBFNN) is applied to guarantee the feasibility of algorithm. Finally, several nonlinear functions are used to validate the effectiveness of the algorithm. Experimental results show that the proposed DCIASORBFNN has achieved better nonlinear approximation ability than that of the art relevant competitors.展开更多
This paper has discussed the possibility and key problem to construct the neural network time series model, and three time series neural network forecasting methods has been proposed, i. e. a neural network nonlinear ...This paper has discussed the possibility and key problem to construct the neural network time series model, and three time series neural network forecasting methods has been proposed, i. e. a neural network nonlinear time series model, a neural network multi-dimension time series model and a neural network combining predictive model. These three methods are applied to real problems. The results show that these methods are better than the traditional one. Furthermore, the neural network methods are compared with the traditional method, and the constructed model of intellectual information forecasting system is given.展开更多
Haze-fog,which is an atmospheric aerosol caused by natural or man-made factors,seriously affects the physical and mental health of human beings.PM2.5(a particulate matter whose diameter is smaller than or equal to 2.5...Haze-fog,which is an atmospheric aerosol caused by natural or man-made factors,seriously affects the physical and mental health of human beings.PM2.5(a particulate matter whose diameter is smaller than or equal to 2.5 microns)is the chief culprit causing aerosol.To forecast the condition of PM2.5,this paper adopts the related the meteorological data and air pollutes data to predict the concentration of PM2.5.Since the meteorological data and air pollutes data are typical time series data,it is reasonable to adopt a machine learning method called Single Hidden-Layer Long Short-Term Memory Neural Network(SSHL-LSTMNN)containing memory capability to implement the prediction.However,the number of neurons in the hidden layer is difficult to decide unless manual testing is operated.In order to decide the best structure of the neural network and improve the accuracy of prediction,this paper employs a self-organizing algorithm,which uses Information Processing Capability(IPC)to adjust the number of the hidden neurons automatically during a learning phase.In a word,to predict PM2.5 concentration accurately,this paper proposes the SSHL-LSTMNN to predict PM2.5 concentration.In the experiment,not only the hourly precise prediction but also the daily longer-term prediction is taken into account.At last,the experimental results reflect that SSHL-LSTMNN performs the best.展开更多
文摘In order to study the problem of intelligent information processing in new types of imaging fuze, the method of extracting the invariance features of target images is adopted, and radial basis function neural network is used to recognize targets. Owing to its ability of parallel processing, its robustness and generalization, the method can realize the recognition of the conditions of missile-target encounters, and meet the requirements of real-time recognition in the imaging fuze. It is shown that based on artificial neural network target recognition and burst point control are feasible.
基金supported by the National Natural Science Foundation of China(NSFC)(62125503,62261160388)the Natural Science Foundation of Hubei Province of China(2023AFA028)the Innovation Project of Optics Valley Laboratory(OVL2021BG004).
文摘In recent years,space-division multiplexing(SDM)technology,which involves transmitting data information on multiple parallel channels for efficient capacity scaling,has been widely used in fiber and free-space optical communication sys-tems.To enable flexible data management and cope with the mixing between different channels,the integrated reconfig-urable optical processor is used for optical switching and mitigating the channel crosstalk.However,efficient online train-ing becomes intricate and challenging,particularly when dealing with a significant number of channels.Here we use the stochastic parallel gradient descent(SPGD)algorithm to configure the integrated optical processor,which has less com-putation than the traditional gradient descent(GD)algorithm.We design and fabricate a 6×6 on-chip optical processor on silicon platform to implement optical switching and descrambling assisted by the online training with the SPDG algorithm.Moreover,we apply the on-chip processor configured by the SPGD algorithm to optical communications for optical switching and efficiently mitigating the channel crosstalk in SDM systems.In comparison with the traditional GD al-gorithm,it is found that the SPGD algorithm features better performance especially when the scale of matrix is large,which means it has the potential to optimize large-scale optical matrix computation acceleration chips.
文摘Temporal information processing in the range of tens to hundreds of milliseconds is critical in many forms of sensory and motor tasks. However, little has been known about the neural mechanisms of temporal information processing. Experimental observations indicate that sensory neurons of the nervous system do not show selective response to temporal properties of external stimuli. On the other hand, temporal selective neurons in the cortex have been reported in many species. Thus, processes which realize the temporal-to-spatial transformation of neuronal activities might be required for temporal information processing. In the present study, we propose a computational model to explore possible roles of electrical synapses in processing the duration of external stimuli. Firstly, we construct a small-scale network with neurons interconnected by electrical synapses in addition to chemical synapses. Basic properties of this small-scale neural network in processing duration information are analyzed. Secondly, a large-scale neural network which is more biologically realistic is further explored. Our results suggest that neural networks with electrical synapses functioning together with chemical synapses can effectively work for the temporal-to-spatial transformation of neuronal activities, and the spatially distributed sequential neural activities can potentially represent temporal information.
基金supported by the Sichuan Science and Technology Program under Grants No.2022YFQ0052 and No.2021YFQ0009.
文摘At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production environments,there are a large number of KGs with a small number of entities and relations,which are called sparse KGs.Limited by the performance of knowledge extraction methods or some other reasons(some common-sense information does not appear in the natural corpus),the relation between entities is often incomplete.To solve this problem,a method of the graph neural network and information enhancement is proposed.The improved method increases the mean reciprocal rank(MRR)and Hit@3 by 1.6%and 1.7%,respectively,when the sparsity of the FB15K-237 dataset is 10%.When the sparsity is 50%,the evaluation indexes MRR and Hit@10 are increased by 0.8%and 1.8%,respectively.
基金supported in part by the National Natural Science Foundation of China under Grant 61461013in part of the Natural Science Foundation of Guangxi Province under Grant 2018GXNSFAA281179in part of the Dean Project of Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing under Grant GXKL06160103.
文摘In this study,we developed a system based on deep space–time neural networks for gesture recognition.When users change or the number of gesture categories increases,the accuracy of gesture recognition decreases considerably because most gesture recognition systems cannot accommodate both user differentiation and gesture diversity.To overcome the limitations of existing methods,we designed a onedimensional parallel long short-term memory–fully convolutional network(LSTM–FCN)model to extract gesture features of different dimensions.LSTM can learn complex time dynamic information,whereas FCN can predict gestures efficiently by extracting the deep,abstract features of gestures in the spatial dimension.In the experiment,50 types of gestures of five users were collected and evaluated.The experimental results demonstrate the effectiveness of this system and robustness to various gestures and individual changes.Statistical analysis of the recognition results indicated that an average accuracy of approximately 98.9% was achieved.
基金supported by the National Natural Science Foundation of China(61890930-5,61533002,61603012)the Major Science and Technology Program for Water Pollution Control and Treatment of China(2018ZX07111005)+1 种基金the National Key Research and Development Project(2018YFC1900800-5)Beijing Municipal Education Commission Foundation(KM201710005025)
文摘Radial basis function neural network(RBFNN) is an effective algorithm in nonlinear system identification. How to properly adjust the structure and parameters of RBFNN is quite challenging. To solve this problem, a distance concentration immune algorithm(DCIA) is proposed to self-organize the structure and parameters of the RBFNN in this paper. First, the distance concentration algorithm, which increases the diversity of antibodies, is used to find the global optimal solution. Secondly,the information processing strength(IPS) algorithm is used to avoid the instability that is caused by the hidden layer with neurons split or deleted randomly. However, to improve the forecasting accuracy and reduce the computation time, a sample with the most frequent occurrence of maximum error is proposed to regulate the parameters of the new neuron. In addition, the convergence proof of a self-organizing RBF neural network based on distance concentration immune algorithm(DCIA-SORBFNN) is applied to guarantee the feasibility of algorithm. Finally, several nonlinear functions are used to validate the effectiveness of the algorithm. Experimental results show that the proposed DCIASORBFNN has achieved better nonlinear approximation ability than that of the art relevant competitors.
文摘This paper has discussed the possibility and key problem to construct the neural network time series model, and three time series neural network forecasting methods has been proposed, i. e. a neural network nonlinear time series model, a neural network multi-dimension time series model and a neural network combining predictive model. These three methods are applied to real problems. The results show that these methods are better than the traditional one. Furthermore, the neural network methods are compared with the traditional method, and the constructed model of intellectual information forecasting system is given.
文摘Haze-fog,which is an atmospheric aerosol caused by natural or man-made factors,seriously affects the physical and mental health of human beings.PM2.5(a particulate matter whose diameter is smaller than or equal to 2.5 microns)is the chief culprit causing aerosol.To forecast the condition of PM2.5,this paper adopts the related the meteorological data and air pollutes data to predict the concentration of PM2.5.Since the meteorological data and air pollutes data are typical time series data,it is reasonable to adopt a machine learning method called Single Hidden-Layer Long Short-Term Memory Neural Network(SSHL-LSTMNN)containing memory capability to implement the prediction.However,the number of neurons in the hidden layer is difficult to decide unless manual testing is operated.In order to decide the best structure of the neural network and improve the accuracy of prediction,this paper employs a self-organizing algorithm,which uses Information Processing Capability(IPC)to adjust the number of the hidden neurons automatically during a learning phase.In a word,to predict PM2.5 concentration accurately,this paper proposes the SSHL-LSTMNN to predict PM2.5 concentration.In the experiment,not only the hourly precise prediction but also the daily longer-term prediction is taken into account.At last,the experimental results reflect that SSHL-LSTMNN performs the best.