中国人工智能发展的时空网络结构及驱动因子研究

通过直觉模糊层次分析法和动态灰色关联法对中国30个省(区、市)在2011—2021年人工智能发展水平进行评测;通过核密度、趋势面和社会网络分析方法分析中国人工智能发展的时间和空间结构,并探测网络空间分异的驱动因子以了解中国人工智能发展状况。结果显示:中国人工智能发展整体水平呈现明显的逐年增长态势,其中2019、2020和2021年增长速度最快。整体发展指数呈现东部大于西部、南部大于北部的空间格局。空间网络的网络等级度和网络效率逐年增加,但网络连接数和网络密度有逐年减少趋势。中部、西部和东北地区板块类型为主受益板块和双向溢出板块,东部地区板块类型为经纪人板块和净溢出板块。驱动因子中R&D经费投入强度、经济发展水平和信息固定资产投资为中国人工智能发展的主要驱动因子。当R&D经费投入强度和经济发展水平这两个驱动因子与其他驱动因子交互时,对中国人工智能发展水平的倍增效应最为显著。

数字振荡器的实现原理与仿真编程

鉴于数字信号处理中的实时应用问题。探讨了数字滤波器的实时实现原理 ,包括离散时间网络结构的作用和离散时间信号处理的特点。重点分析了实时应用中实现数字滤波器的基本思想 ,运用 MATL AB和所导出的通用数字振荡器的系统函数对一个非正弦数字振荡器进行了仿真编程。还讨论了有关实时处理的几个重要的系统性质 ,表达了作者对于当前学习和应用数字信号处理方法的观点。

Remarks on the Efficiency of Bionic Optimisation Strategies

Bionic optimisation is one of the most popular and efficient applications of bionic engineering. As there are many different approaches and terms being used, we try to come up with a structuring of the strategies and compare the efficiency of the different methods. The methods mostly proposed in literature may be classified into evolutionary, particle swarm and artificial neural net optimisation. Some related classes have to be mentioned as the non-sexual fern optimisation and the response surfaces, which are close to the neuron nets. To come up with a measure of the efficiency that allows to take into account some of the published results the technical optimisation problems were derived from the ones given in literature. They deal with elastic studies of frame structures, as the computing time for each individual is very short. General proposals, which approach to use may not be given. It seems to be a good idea to learn about the applicability of the different methods at different problem classes and then do the optimisation according to these experiences. Furthermore in many cases there is some evidence that switching from one method to another improves the performance. Finally the identification of the exact position of the optimum by gradient methods is often more efficient than long random walks around local maxima.

Prediction of Temperature Daily Profile by Stochastic Update of Backpropagation through Time Algorithm

The authors will examine prediction of temperature daily profile using various modifications of BPTT （backpropagation through time algorithm） done by stochastic update in the artificial RCNN （recurrent neural networks）. The general introduction was provided by Salvetti and Wilamowski in 1994 in order to improve probability of convergence and speed of convergence. This update method has also one another quality, its implementation is simple for arbitrary network topology. In stochastic update scenario, constant number of weights/neurons is randomly selected and updated. This is in contrast to classical ordered update, where always all weights/neurons are updated. Stochastic update is suitable to replace classical ordered update without any penalty on implementation complexity and with good chance without penalty on quality of convergence. They have provided first experiments with stochastic modification on BP （backpropagation algorithm） used for artificial FFNN （feed-forward neural network） in detail described in the article ＂Stochastic Weight Update in the Backpropagation Algorithm on Feed-Forward Neural Networks＂ presented on the conference IJCNN （International Joint Conference of Neural Networks） 2010 in Barcelona. The BPTT on RCNN uses the history of previous steps stored inside of the NN that can be used for prediction. They will describe exact implementation on the RCNN, and present experiment results on temperature prediction with recurrent neural network topology. The dataset used for temperature prediction consists of the measured temperature from the year 2000 till the end of February 2011. Dataset is split into two groups： training dataset, which is provided to network in learning phase, and testing dataset, which is unknown part of dataset to NN and used to test the ability of NN to predict the temperature and the ability of NN to generalize the model hidden in the temperature profile. The results show promising properties of stochastic weight update with toy-task data, and the higher complexity of the temperature daily profile prediction.

ROBUSTNESS ANALYSIS OF LEADER-FOLLOWER CONSENSUS

In this paper,robustness properties of the leader-follower consensus are considered.Forsimplicity of presentation,the attention is focused on a group of continuous-time first-order dynamicagents with a time-invariant communication topology in the presence of communication errors.In orderto evaluate the robustness of leader-follower consensus,two robustness measures are proposed:the L_2gain of the error vector to the state of the network and the worst case L_2 gain at a node.Althoughthe L_2 gain of the error vector to the state of the network is widely used in robust control design andanalysis,the worst case L_2 gain at a node is less conservative with respect to the number of nodes inthe network.It is thus suggested that the worst case L_2 gain at a node is used when the robustnessof consensus is considered.Theoretical analysis and simulation results show that these two measuresare sensitive to the communication topology.In general,the 'optimal' communication topology thatcan achieve most robust performance with respect to either of the proposed robustness measures isdifficult to characterize and/or obtain.When the in-degree of each follower is one,it is shown thatboth measures reach a minimum when the leader can communicate to each node in the network.

Synchronization Research of a Modified Time-Delayed Multi-agent Network Model

The synchronization of time-delayed multi-agent networks with connected and directed topology is studied. Based on the correlative work about the agent synchronization, a modified model is presented, in which each communication receiver is distributed a delay 7. In addition, a proportional term k is introduced to modulate the delay range and to guarantee the synchronization of each agent. Two new parameters mentioned above are only correlative to the network topology, and a theorem about their connections is derived by both frequency domain method and geometric method. Finally, the theoretical result is illustrated by numerical simulations.