基于DNA链置换的赢家通吃神经网络

DNA链置换技术广泛用于生物计算中,在计算能力和信息处理方面表现出色.但是,在信号的放大、恢复与比较等一些计算中使用DNA链置换技术,不仅增加DNA链的数量,还会带来额外的计算成本.因此,为了减少DNA链的使用数量,该文构建了一个基于DNA链置换实现的赢家通吃(WTA)神经网络.首先,通过神经元实现逻辑运算AND,NAND和OR,将其级联成WTA神经网络解决了线性不可分问题.通过与别人结果的比较,证明该文采用方法的有效性,并在Visual DSD(DNA链置换)中获得了稳定而直观的结果.然后,为了检验神经元级联的可扩展性,设计了一个3人表决器,并对科学家进行分类,该文展示了分子系统如何表现出与大脑具有类似行为的思考能力,最后证明获得的准确率高于其他方法.     

基于DNA链置换的两位格雷码减法器分子电路设计

DNA链置换技术具有自发性、并行性、可编程性、动态级联性的特点，在DNA计算中占据重要的地位。DNA链置换技术被广泛的应用于解决数学问题，该文采用格雷码编码方式结合DNA链置换技术设计了两位减法器，扩展DNA减法运算。最后利用Visual DSD软件模拟两位减法器，该电路达到预期的功能，且具有并行性和可扩展性，可与其他生化电路结合使用。     

具有非线性映射特性的量子神经元

介绍了与量子神经网络相关的量子计算基础，描述了一种量子神经元模型，分析了该模型的量子运算特性。分析和实验证明单个量子神经元能实现经典神经元无法实现的XOR函数，并具有与两层前向神经网络相当的非线性映射能力。     

量子衍生神经网络的设计与实现

当使用神经网络解决问题时, 得到的结果与神经网络的逼近能力有很大关系。如何提高神经网络的逼近能力目前还没有较为理想的解决方法。本文提出了一种利用多位量子受控非门来构造神经网络模型的新方法。该模型为三层结构,隐层为量子神经元,输出层为普通神经元。量子神经元由量子旋转门和多位受控非门组成,利用多位受控非门中目标量子位的输出向输入端的反馈,实现对输入序列的整体记忆,利用多位受控非门的受控关系获得量子神经元的输出。基于量子计算原理设计了该模型的L M学习算法。该模型可从宽度和深度两方面获取输入序列的特征。纸牌预测的实验结果表明,当输入节点数和序列长度比较接近时,该模型对训练集的识别率比普通神经网络有大约8%的提高,从而揭示了量子计算机制对提高网络逼近能力的有效性。      

量子神经元特性研究

量子神经计算是传统神经计算自然演化发展的产物，它有可能成为新的信息处理技术。本文介绍了与量关的量子计算基础，描述了一种量子神经元模型，提出了一种量子学习算法，通过理论推导和仿真证明了算法的收敛性并给出了几种收敛特性曲线.应用量子计算方法分析了该量子神经元模型的量子逻辑运算功能,分析和实验证明了单个量子神经元能实现经典神经元无法实现的XOR函数,并具有与两层前向神经网络相当的非线性映射能力.     

基于DNA链置换的三级联组合分子逻辑电路设计

DNA计算研究内容繁多复杂,DNA复杂逻辑电路的搭建属于DNA计算的一个重要研究分支,其中逻辑门的构建属于DNA复杂逻辑电路搭建的基础研究,设计出更为简单的逻辑门可以为研究者搭建复杂电路提供参考,节省基础研究的宝贵时间。针对上述问题,该文利用使能控制端思想,采用DNA链置换技术,设计了与或、与非或非和异或同或3种DNA组合逻辑门。结果显示,设计的3种组合逻辑门可实现6种逻辑运算功能,并利用所构建的组合逻辑门成功构造了多级联组合分子逻辑电路,为DNA计算提供了更多的解决方案,促进了DNA计算机的发展。     

基于DNA折纸基底的与非门计算模型

与非门(NAND)的本质是与门(AND)和非门(NOT)的叠加,先进行与运算,再进行非运算,它是建立DNA计算机的基础。为了实现与非门的计算,该文在DNA折纸基底上建立了一个与非门计算模型,逻辑值的输入是通过在DNA折纸基底上发生有向的杂交链式反应(HCR)来完成的,输入链先经过与门区域再经过非门区域,最后通过DNA折纸基底上是否还保留纳米金颗粒来显示计算结果的真假。利用Visual DSD对该计算模型进行仿真模拟,显示该计算模型具有较好的可行性。     

G神经网络函数映射能力的构造性证明

该文研究了G神经网络的函数映射能力,给出了前馈G神经网络映射任意G型多项式的构造性证明。采用该文的方法映射同一个多项式,所用的神经元数目可少至以往方法的2/(n+1),其中n是G型多项式的次数。     

激光雷达距离估计技术

距离估计技术一直是激光雷达技术中的核心技术,对整个激光雷达系统性能的优劣性起到决定性作用。提出了一种基于人工神经网络的距离估计算法,使用的人工神经网络由两层网络构成。与交叉相关距离估计算法的对比实验证明:基于人工神经网络的距离估计算法在实际应用中有更高的距离估计精度;对强度像进行了仿真实验,实验结果证明:基于人工神经网络的距离估计算法相比极值判别法能够获得更精准的回波强度信息;对神经网络隐含层中神经元个数与距离估计精度之间的关系进行了实验分析,实验结果证明:过多或过少的神经元个数均会降低距离估计精度。     

基于DNA和限制性核酸内切酶的基本逻辑门设计

由于DNA分子具有特异性、高并行性、微小性等天然特性,在信息处理过程中展现出了强大的并行计算能力和数据存储能力。该文研究将具有特异性识别功能的限制性核酸内切酶引入DNA链置换反应中,作为DNA电路的输入,通过控制立足点的生成和移除设计了是门、非门和与门3种基本逻辑门。采用Visual DSD对逻辑模型进行模拟仿真,并通过凝胶电泳实验验证设计。与以往的分子逻辑门比较,该设计反应迅速,操作简便,具有良好的扩展性,为大规模电路的设计提供了可能性。     

KWTA networks and their applications

Winner-Take-All (WTA) or K-Winner-Take-All (KWTA) networks have been frequently used as the basic building blocks of complex neural networks. This paper introduces a new selection rule for network connections that implements stable KWTA networks. To widen the applications of WTA networks, a new class of WTA networks is proposed, and their efficient design methods are presented. We demonstrate the properties of the generalized class of WTA networks, through three application examples.     

Single-electron winner-take-all network

A winner-take-all (WTA) single-electron neuron is developed for the first time. This new single-electron circuit is proposed in order to implement a WTA neural network with lateral inhibition architecture. An expression for the neuron's activation function is presented. Furthermore, a dot pattern recognition task is successfully performed by the implemented network considering effects such as offset charges and co-tunnelling.     

电流型汉明神经网络的设计

本文提出了两种新的电流型汉明神经网络电路。第一种风络包括电流型模板匹配电路和全互连的电流型求大网络，结构简单，没有时钟模拟显示该电路具有高速度、高精度和低功耗等特点。在该电路的基础上，又提出了一种采用电流型模板匹配电路和电压型求大网络的汉明神经网络电路，同样具有上述特点。     

A high-precision VLSI winner-take-all circuit for self-organizingneural networks

The design and implementation of a high-precision VLSI winner-take-all (WTA) circuit that can be arranged to process 1024 inputs are presented. The cascade configuration can be used to significantly increase the competition resolution and maintain high-speed operation for a large-scale network. The total bias current increases in proportion to the number of circuit cells so that a nearly constant response time is achieved. A unique dynamic current steering method is used to ensure that only a single winner exits in the final output. Experimental results for a prototype chip fabricated in a 2-μm CMOS technology show that a cell can be a winner if its input is larger than those of the other cells by 15 mV. The measured response time is around 50 ns at a 1-pF load capacitance. This analog winner-take-all circuit is a key module in the competitive layer of self-organizing neural networks     

一种基于分治的三维匹配问题DNA计算算法

 本文基于Aldeman-Lipton模型的生物操作与粘贴模型的解空间,提出一种三维匹配问题的DNA计算新模型;同时基于此模型和传统计算机中分治策略,提出一种求解三维匹配问题的DNA计算新算法.将提出的算法与已有文献结论的对比分析表明:本算法将穷举算法中的DNA链数从O(2ⁿ)减少至O(2^n/2)≈O(1.414ⁿ),同时生物操作数由O(n²)减少至O(15n+30q),测试试管数由所需的O(n)减少至O(1),最大链长由O(15n+45q)减少至O(15n/2+45q).因此,本算法理论上在试管级生化反应条件下能将求解三维匹配问题的规模从67(2⁶⁷≈10²²)提高到134(67×2=134).同时,与传统的穷举搜索算法相比,该算法具有高效的空间利用率及容错技术的优点.     

Energy Efficient Resource Scheduling Using Optimization Based Neural Network in Mobile Cloud Computing

The mobile cloud computing has become an emerging technology where the mobile computing is integrated with cloud computing to process the mobile data. Besides the advantages of mobile cloud computing, there are some issues which include power consumption, resource scarcity, quality of service, security and computational cost. In this paper, in order to minimize total power consumption with better performance, the neural network based optimization methods using artificial neural network and convolutional neural network models were implemented by varying variance and loudness. From the experimental results it is observed that, by using optimization in the neural network, the power consumption has been reduced by 53.68% and obtained improvement using convolutional neural network which further reduced the power consumption by 30.3% with minimum root mean square error compared with other algorithms.

     

CSM neural network for degraded printed character optical recognition

In pattern recognition applications, the classification power of a system can be improved by combining several classifiers. Obviously performance of the system cannot be improved if the individual classifiers make all the same mistakes, thus it is important to use different features and different structures in the individual classifiers. In this context, we propose a two subnets neural network called CSM net. The first subnet, or similarity layer, is operating as a similarity measure neural network; it is based on the complementary similarity measure method (CSM). The second subnet is a competitive neural network (CNN) based on the winner takes all algorithm (WTA) that is used for the classification. In the proposed neural architecture, the statistical CSM method is analyzed, and implemented in the form of a feed forward neural network, it is named “similarity measure neural network” (SMNN). We show that the resulting SMNN synaptic weights are modified versions of the model patterns used in the training set, and that they can be considered as a memory network. We introduce a relative distance data calculated from the SMNN output, and we use it as a quality measurement tool of the degraded characters, what makes the SMNN classifier very powerful, and very well-suited for features rejections. This relative distance is used by the SMNN and compared to a first rejection threshold to accept, or reject, the incoming characters. In order to guarantee a higher recognition and reliability rates for the cascaded method, the SMNN is combined with a second subnet based on the WTA for classification using a second specific rejection threshold. These two submits combination (CSM net) boost the performance of the SMNN classifier. This is resulting in a robust multiple classifiers that can be used for setting the entire rejection threshold. The experimental results that we introduce are related to the proposed method, but the tests are introduced with various impulse noise levels, as well as the tests with broken and manually corrupted characters, and characters with various levels of additive Gaussian noise. The experiments show the effective ability of the model to yield relevant and robust recognition on poor quality printed checks, and show that the CSM net outperforms the previous works, both in efficiency and accuracy.