Reinforcement Learning Based Quantization Strategy Optimal Assignment Algorithm for Mixed Precision

The quantization algorithm compresses the original network by reducing the numerical bit width of the model,which improves the computation speed. Because different layers have different redundancy and sensitivity to databit width. Reducing the data bit width will result in a loss of accuracy. Therefore, it is difficult to determinethe optimal bit width for different parts of the network with guaranteed accuracy. Mixed precision quantizationcan effectively reduce the amount of computation while keeping the model accuracy basically unchanged. In thispaper, a hardware-aware mixed precision quantization strategy optimal assignment algorithm adapted to low bitwidth is proposed, and reinforcement learning is used to automatically predict the mixed precision that meets theconstraints of hardware resources. In the state-space design, the standard deviation of weights is used to measurethe distribution difference of data, the execution speed feedback of simulated neural network accelerator inferenceis used as the environment to limit the action space of the agent, and the accuracy of the quantization model afterretraining is used as the reward function to guide the agent to carry out deep reinforcement learning training. Theexperimental results show that the proposed method obtains a suitable model layer-by-layer quantization strategyunder the condition that the computational resources are satisfied, and themodel accuracy is effectively improved.The proposed method has strong intelligence and certain universality and has strong application potential in thefield of mixed precision quantization and embedded neural network model deployment.

Dimension-down iterative algorithm for the mixed transportation network design problem

An optimal dimension-down iterative algorithm （DDIA） is proposed for solving a mixed （continuous/ discrete） transportation network design problem （MNDP）, which is generally expressed as a mathematical programming with equilibrium constraints （MPEC）. The upper level of the MNDP aims to optimize the network performance via both the expansion of existing links and the addition of new candidate links, whereas the lower level is a traditional Wardrop user equilibrium （UE） model. The idea of the proposed DDIA is to reduce the dimensions of the problem. A group of variables （discrete/continuous） are fixed to altemately optimize another group of variables （continuous/discrete）. Some continuous network design problems （CNDPs） and discrete network design problems （DNDPs） are solved repeatedly until the optimal solution is obtained. A numerical example is given to demonstrate the efficiency of the proposed algorithm.

ADAPTIVE PINNING SYNCHRONIZATION OF COUPLED NEURAL NETWORKS WITH MIXED DELAYS AND VECTOR-FORM STOCHASTIC PERTURBATIONS

In this article, we consider the global chaotic synchronization of general cou- pled neural networks, in which subsystems have both discrete and distributed delays. Stochastic perturbations between subsystems are also considered. On the basis of two sim- ple adaptive pinning feedback control schemes, Lyapunov functional method, and stochas- tic analysis approach, several sufficient conditions are developed to guarantee global syn- chronization of the coupled neural networks with two kinds of delay couplings, even if only partial states of the nodes are coupled. The outer-coupling matrices may be symmetric or asymmetric. Unlike existing results that an isolate node is introduced as the pinning target, we pin to help the network realizing synchronization without introducing any iso- late node when the network is not synchronized. As a by product, sufficient conditions under which the network realizes synchronization without control are derived. Numerical simulations confirm the effectiveness of the obtained results.

Dynamic Analysis of Some Impulsive Fractional-Order Neural Network with Mixed Delay

In this paper,the authors study some impulsive fractionalorder neural network with mixed delay. By the fractional integral and the definition of stability, the existence of solutions of the network is proved,and the sufficient conditions for stability of the system are presented. Some examples are given to illustrate the main results.

Prediction of tree crown width in natural mixed forests using deep learning algorithm

Crown width(CW)is one of the most important tree metrics,but obtaining CW data is laborious and timeconsuming,particularly in natural forests.The Deep Learning(DL)algorithm has been proposed as an alternative to traditional regression,but its performance in predicting CW in natural mixed forests is unclear.The aims of this study were to develop DL models for predicting tree CW of natural spruce-fir-broadleaf mixed forests in northeastern China,to analyse the contribution of tree size,tree species,site quality,stand structure,and competition to tree CW prediction,and to compare DL models with nonlinear mixed effects(NLME)models for their reliability.An amount of total 10,086 individual trees in 192 subplots were employed in this study.The results indicated that all deep neural network(DNN)models were free of overfitting and statistically stable within 10-fold cross-validation,and the best DNN model could explain 69%of the CW variation with no significant heteroskedasticity.In addition to diameter at breast height,stand structure,tree species,and competition showed significant effects on CW.The NLME model(R^(2)=0.63)outperformed the DNN model(R^(2)=0.54)in predicting CW when the six input variables were consistent,but the results were the opposite when the DNN model(R^(2)=0.69)included all 22 input variables.These results demonstrated the great potential of DL in tree CW prediction.

Global exponential stability of mixed discrete and distributively delayed cellular neural network

This paper concernes analysis for the global exponential stability of a class of recurrent neural networks with mixed discrete and distributed delays. It first proves the existence and uniqueness of the balance point, then by employing the Lyapunov-Krasovskii functional and Young inequality, it gives the sufficient condition of global exponential stability of cellular neural network with mixed discrete and distributed delays, in addition, the example is provided to illustrate the applicability of the result.

Attention-based novel neural network for mixed frequency data

It is a common fact that data(features,characteristics or variables)are collected at different sampling frequencies in some fields such as economic and industry.The existing methods usually either ignore the difference from the different sampling frequencies or hardly take notice of the inherent temporal characteristics in mixed frequency data.The authors propose an innovative dual attention-based neural network for mixed frequency data(MID-DualAtt),in order to utilize the inherent temporal characteristics and select the input characteristics reasonably without losing information.According to the authors’knowledge,this is the first study to use the attention mechanism to process mixed fre-quency data.The MID-DualAtt model uses the frequency alignment method to trans-form the high--frequency variables into observation vectors at low frequency,and more critical input characteristics are selected for the current prediction index by attention mechanism.The temporal characteristics are explored by the encoder-decoder with attention based on long-short-term memory networks(LSTM).The proposed MID-DualAtt has been tested in practical application,and the experimental results show that it has better prediction ability than the compared models.

Identification of Key Links in Electric Power Operation Based-Spatiotemporal Mixing Convolution Neural Network

As the scale of the power system continues to expand,the environment for power operations becomes more and more complex.Existing risk management and control methods for power operations can only set the same risk detection standard and conduct the risk detection for any scenario indiscriminately.Therefore,more reliable and accurate security control methods are urgently needed.In order to improve the accuracy and reliability of the operation risk management and control method,this paper proposes a method for identifying the key links in the whole process of electric power operation based on the spatiotemporal hybrid convolutional neural network.To provide early warning and control of targeted risks,first,the video stream is framed adaptively according to the pixel changes in the video stream.Then,the optimized MobileNet is used to extract the feature map of the video stream,which contains both time-series and static spatial scene information.The feature maps are combined and non-linearly mapped to realize the identification of dynamic operating scenes.Finally,training samples and test samples are produced by using the whole process image of a power company in Xinjiang as a case study,and the proposed algorithm is compared with the unimproved MobileNet.The experimental results demonstrated that the method proposed in this paper can accurately identify the type and start and end time of each operation link in the whole process of electric power operation,and has good real-time performance.The average accuracy of the algorithm can reach 87.8%,and the frame rate is 61 frames/s,which is of great significance for improving the reliability and accuracy of security control methods.

Multicomponent mixed metallic hierarchical ZnNi@Ni@PEDOT arrayed structures as advanced electrode for high-performance hybrid electrochemical cells

Engineering multicomponent nanomaterials as an electrode with rationalized ordered structures is a promising strategy for fulfilling the high-energy storage needs of supercapacitors(SCs).Even now,the fundamental barrier to utilizing hydroxides/hydroxyl carbonates is their poor electrochemical performance,resulting from the significantly poor electrical conductivity and sluggish charge storage kinetics.Hence,a multilayered structural approach is primarily and successfully used to construct electrodes as one of the efficient approaches.This method has made it possible to develop well-ordered nanostructured electrodes with good performance by taking advantage of tunable approach parameters.Herein,we report the design of multilayered heterostructure porous zinc-nickel nanosheets@nickel flakes hydroxyl carbonates and/or hydroxides integrated with conductive PEDOT fibrous network(i.e.,ZnNi@Ni@PEDOT) via facile synthesis methods.The combined hybrid electrode acquires the features of high electrical conductivity from one part and various valance states from another one to develop a well-organized nanosheet/flake/fibrous-like heterostructure with decent mechanical strength,creating robust synergistic results.Thus,the designed binder-free ZnNi@Ni@PEDOT electrode delivers a high areal capacity value of 1050.1 μA h cm^(-2) at 3 mA cm^(-2) with good cycling durability,significantly outperforming other individual electrodes.Moreover,its feasibility is also tested by constructing a hybrid electrochemical cell(HEC).The assembled HEC exhibits a high areal capacity value of 783.8 μA h cm^(-2) at5 mA cm^(-2).and even at a high current density of 100 mA cm^(-2)(484.6 μA h cm^(-2)),the device still retains a rate capability of 61,82%,Also,the HEC shows maximum energy and power densities of0.595 mW h cm^(-2) and 77.23 mW cm^(-2),respectively,along with good cycling stability.The obtained energy storage capabilities effectively power various electronic components.These results provide a viable and practical way to construct a positive electrode with innovative heterostructures for highperformance energy storage devices and profoundly influence the development of electrochemical SCs.

A mixed stochastic user equilibrium model considering influence of advanced traveller information systems in degradable transport network

Advanced traveler information systems （ATIS） can not only improve drivers＇ accessibility to the more accurate route travel time information, but also can improve drivers＇ adaptability to the stochastic network capacity degradations. In this paper, a mixed stochastic user equilibrium model was proposed to describe the interactive route choice behaviors between ATIS equipped and unequipped drivers on a degradable transport network. In the proposed model the information accessibility of equipped drivers was reflected by lower degree of uncertainty in their stochastic equilibrium flow distributions, and their behavioral adaptability was captured by multiple equilibrium behaviors over the stochastic network state set. The mixed equilibrium model was formulated as a fixed point problem defined in the mixed route flows, and its solution was achieved by executing an iterative algorithm. Numerical experiments were provided to verify the properties of the mixed network equilibrium model and the efficiency of the iterative algorithm.

Performance Analysis of Mixed Amplify-and-Forward and Decode-and-Forward Protocol in Underlay Cognitive Networks

In this paper, we propose and evaluate outage performance of a mixed amplify-and-forward(AF) and decode-and-forward(DF) relaying protocol in underlay cognitive radio. Different from the conventional AF and DF protocols, in the proposed protocol, a secondary source attempts to transmit its signal to a secondary destination with help of two secondary relays. One secondary relay always operates in AF mode, while the remaining one always operates in DF mode. Moreover, we also propose a relay selection method, which relies on the decoding status at the DF relay. For performance evaluation and comparison, we derive the exact and approximate closedform expressions of the outage probability for the proposed protocol over Rayleigh fading channel. Finally, we run Monte Carlo simulations to verify the derivations. Results presented that the proposed protocol obtains a diversity order of three and the outage performance of our scheme is between that of the conventional underlay DF protocol and that of the conventional underlay AF protocol.

PON and WiMAX Convergence Network Planning Based on Mixed Integer Programming Model

This article analyzes the characteristics of PON and WiMAX convergence network planning.Based on user coverage ratio,WiMAX channel allocation,cell radius,carrier-to-noise ratio threshold,and bandwidth constraint,we propose a mixed integer programming model solved by a Branch-Band and Heuristic Search method.Finally,the simulation result is given and analyzed.The planning method based on a mixed integer programming model can save 20 percentage of the overall planning cost,compared with the greedy algorithm.The relationship between the convergence network planning cost and frequency usage is also analyzed.The optimized planning result with the lowest cost can be acquired through the best frequency usage.

Existence and Exponential Stability of the Anti-Periodic Solutions for a Class of Impulsive CohenGrossberg Neural Networks with Mixed Delays

In this paper,we study the anti-periodic solutions for a class of impulsive Cohen-Grossberg neural networks with mixed delays.By using analysis techniques,some sufficient conditions are obtained which guarantee the existence and global exponential stability of the anti-periodic solutions.The criteria extend and improve some earlier results.Moreover,we give an examples to illustrate our main results.

Equilibrium analysis of mixed passengers in urban railway network

A model is proposed to describe the passengers’route choice behaviors in urban railway traffic with stochastic link capacity degradation by considering two types of demand,sensitive and insensitive passenger.The insensitive passengers choose their route without paying much attention to congestion.To the contrary,sensitive passengers who consider route congestion choose travel route based on generalized cost.An equilibrium state is given by variational inequalities in terms of travel generalized cost,which is represented by the combinations of mean and variance of total travel time.The diagonalization algorithm is given to solve this programming.Results show that insensitive passengers have large effects on the path choice than sensitive ones,especially for the larger demand.

The Sensitivity of Model Results to Specification of Network-Based Level of Service Attributes: An Application of a Mixed Logit Model to Trave Mode Choice

The need for travel demand models is growing worldwide. Obtaining reasonably accurate level of service (LOS) attributes of different travel modes such as travel time and cost representing the performance of transportation system is not a trivial task, especially in growing cities of developing countries. This study investigates the sensitivity of results of a travel mode choice model to different specifications of network-based LOS attributes using a mixed logit model. The study also looks at the possibilities of correcting some of the inaccuracies in network-based LOS attributes. Further, the study also explores the effects of different specifications of LOS data on implied values of time and aggregation forecasting. The findings indicate that the implied values of time are very sensitive to specification of data and model implying that utmost care must be taken if the purpose of the model is to estimate values of time. Models estimated on all specifications of LOS-data perform well in prediction, likely suggesting that the extra expense on developing a more detailed and accurate network models so as to derive more precise LOS attributes is unnecessary for impact analyses of some policies.

A MULTIPLE-RECEPTION ACCESS PROTOCOL WITH INTERRUPTIONS WITH MIXED PRIORITIES IN CDMA NETWORKS

A novel access protocol called Multiple-Reception Access Protocol (WRAP) and its modification MRAP/WI are proposed. In this protocol, all colliding users with a common code can be identified by the base station due to the offset of arrival time. Thus they can retransmit access requests under the base station's control. Furthermore new arrivals with higher priority level can interrupt the lower retransmission in order to reduce its access delay although it, increases the lower priority's delay. Simulation results of MRAP and MRAP/WI are given in order to highlight the superior performance of the proposed approach.

Separability of Pure States and Mixed States of the Quantum Network of Two Nodes

This article discusses the separability of the pure states and mixed states of the quantum network of two nodes by means of the criterion of no entanglement in terms of the covariance correlation tensor in quantum network theory, i.e. for a composite system consisting of two nodes. The covariance correlation tensor is equal to zero for all possible and .

End-to-end Delay Analysis for Mixed-criticality WirelessHART Networks

WirelessHART, as a robust and reliable wireless protocol, has been widely-used in industrial wireless sensoractuator networks. Its real-time performance has been extensively studied, but limited to the single criticality case. Many advanced applications have mixed-criticality communications, where different data flows come with different levels of importance or criticality. Hence, in this paper, we study the real-time mixedcriticality communication using WirelessHART protocol, and propose an end-to-end delay analysis approach based on fixed priority scheduling. To the best of our knowledge, this is the first work that introduces the concept of mixed-criticality into wireless sensor-actuator networks. Evaluation results show the effectiveness and efficacy of our approach. © 2014 Chinese Association of Automation.

Pre-Training Physics-Informed Neural Network with Mixed Sampling and Its Application in High-Dimensional Systems

Recently,the physics-informed neural network shows remarkable ability in the context of solving the low-dimensional nonlinear partial differential equations.However,for some cases of high-dimensional systems,such technique may be time-consuming and inaccurate.In this paper,the authors put forward a pre-training physics-informed neural network with mixed sampling(pPINN)to address these issues.Just based on the initial and boundary conditions,the authors design the pre-training stage to filter out the set of the misfitting points,which is regarded as part of the training points in the next stage.The authors further take the parameters of the neural network in Stage 1 as the initialization in Stage 2.The advantage of the proposed approach is that it takes less time to transfer the valuable information from the first stage to the second one to improve the calculation accuracy,especially for the high-dimensional systems.To verify the performance of the pPINN algorithm,the authors first focus on the growing-and-decaying mode of line rogue wave in the Davey-Stewartson I equation.Another case is the accelerated motion of lump in the inhomogeneous Kadomtsev-Petviashvili equation,which admits a more complex evolution than the uniform equation.The exact solution provides a perfect sample for data experiments,and can also be used as a reference frame to identify the performance of the algorithm.The experiments confirm that the pPINN algorithm can improve the prediction accuracy and training efficiency well,and reduce the training time to a large extent for simulating nonlinear waves of high-dimensional equations.

Almost periodic solutions of memristive multidirectional associative memory neural networks with mixed time delays

Traditional biological neural networks cannot simulate the real situation of the abrupt synaptic connections between neurons while modeling associative memory of human brains.In this paper,the memristive multidirectional associative memory neural networks(MAMNNs)with mixed time-varying delays are investigated in the sense of Filippov solution.First,three steps are given to prove the existence of the almost periodic solution.Two new lemmas are proposed to prove the boundness of the solution and the asymptotical almost periodicity of the solution by constructing Lyapunov function.Second,the uniqueness and global exponential stability of the almost periodic solution of memristive MAMNNs are investigated by a new Lyapunov function.The sufficient conditions guaranteeing the properties of almost periodic solution are derived based on the relevant definitions,Halanay inequality and Lyapunov function.The investigation is an extension of the research on the periodic solution and almost periodic solution of bidirectional associative memory neural networks.Finally,numerical examples with simulations are presented to show the validity of the main results.