Search - minimum energy

Search - minimum energy - List

[AI-NN-PR] hopfild1 DL : 0: Hopfield 网——擅长于联想记忆与解迷路实现H网联想记忆的关键，是使被记忆的模式样本对应网络能量函数的极小值。设有M个N维记忆模式，通过对网络N个神经元之间连接权 wij 和N个输出阈值θj的设计，使得: 这M个记忆模式所对应的网络状态正好是网络能量函数的M个极小值。比较困难，目前还没有一个适应任意形式的记忆模式的有效、通用的设计方法。 H网的算法 1）学习模式——决定权重想要记忆的模式，用-1和1的2值表示模式：-1，-1，1，-1，1，1，... 一般表示：则任意两个神经元j、i间的权重： wij=∑ap(i)ap(j)，p=1…p； P：模式的总数 ap(s)：第p个模式的第s个要素（-1或1） wij：第j个神经元与第i个神经元间的权重 i = j时，wij=0，即各神经元的输出不直接返回自身。 2)想起模式：神经元输出值的初始化想起时，一般是未知的输入。设xi(0)为未知模式的第i个要素（-1或1）将xi(0)作为相对应的神经元的初始值，其中，0意味t=0。反复部分：对各神经元，计算： xi (t+1) = f (∑wijxj（t）-θi), j=1…n, j≠i n—神经元总数 f（）--Sgn（） θi—神经元i发火阈值反复进行，直到各个神经元的输出不再变化。-Hopfield network-- good at associative memory solution with the realization of lost H associative memory networks, are key to bringing the memory model samples corresponding network energy function of the minimum. With M-N-dimensional memory model, the network N neurons connect between right wij and N output threshold j design makes : M-mode memory corresponding to the network is a state network energy function is the M-000 minimum. More difficult, it is not an arbitrary form of adaptation memory model of effective, common design methods. H network algorithm 1) mode of learning-- decision weights want memory model, with 1 and 2 of the value of a model, said :-1, 1, 1, 1 ,1,1, ... in general : two were arbitrary neuron j i weights between : wij ap = (i) ap (j), p = 1 ... p; P : The tot
Date : 2025-12-23 Size : 11kb User : 韵子
[AI-NN-PR] ogaf2 DL : 0: 蚂蚁优化蛋白质序列，找到蛋白质序列的能量函数的最小值-Ant colony optimization for protein sequences, protein sequences to find the minimum energy function
Date : 2025-12-23 Size : 6kb User : zhaochuanmin
[AI-NN-PR] mnth DL : 0: 模拟退火算法来源于固体退火原理，将固体加温至充分高，再让其徐徐冷却，加温时，固体内部粒子随温升变为无序状，内能增大，而徐徐冷却时粒子渐趋有序，在每个温度都达到平衡态，最后在常温时达到基态，内能减为最小。根据Metropolis准则，粒子在温度T时趋于平衡的概率为e-ΔE/(kT)，其中E为温度T时的内能，ΔE为其改变量，k为Boltzmann常数。用固体退火模拟组合优化问题，将内能E模拟为目标函数值f，温度T演化成控制参数t，即得到解组合优化问题的模拟退火算法：由初始解i和控制参数初值t开始，对当前解重复“产生新解→计算目标函数差→接受或舍弃”的迭代，并逐步衰减t值，算法终止时的当前解即为所得近似最优解，这是基于蒙特卡罗迭代求解法的一种启发式随机搜索过程。退火过程由冷却进度表(Cooling Schedule)控制，包括控制参数的初值t及其衰减因子Δt、每个t值时的迭代次数L和停止条件S。 -Simulated annealing algorithm derived from the theory of solid annealing, the solid heat to full high and let it slowly cooling, heating, the temperature rise inside the solid particles with the shape into disorder, which can be increased gradually while slowly cooling particles increasingly ordered, the temperature has reached equilibrium in each state, and finally reached the ground state at room temperature, which can be reduced to minimum. According to Metropolis criterion, particles tend to equilibrium at a temperature T, the probability e-ΔE/(kT), where E is the temperature T, internal energy, ΔE change its volume, k the Boltzmann constant. Simulated annealing with a solid portfolio optimization problem, the internal energy E is modeled as the objective function value f, temperature T evolved into control parameter t, which are solutions of combinatorial optimization problems of the simulated annealing algorithm: the initial solution from the initial value of t i and the control
Date : 2025-12-23 Size : 5kb User : leansmall
[AI-NN-PR] proj07-01 DL : 0: 试验中使用模拟退火算法寻找一6-单元网络能量最小化的模型。模拟退火算法是模拟物理学上的退火技术。其优势在于有可能使系统从局部极小值跳出。-Simulated annealing algorithm used in the experiments to find a 6- unit network model of energy minimization. Simulated annealing algorithm simulates the physics of annealing. The advantage is likely to make the system jump from local minimum.
Date : 2025-12-23 Size : 14kb User : 王瑶
[AI-NN-PR] Image_Feature_Selection_Method_Based_on_Immune_Enc DL : 0: 针对目标与背景两类图像模式识别问题,在已有的特征选择方法基础上,提出了一种新颖的基于免疫分子编码机理的图像特征选择方法(IACA). 该方法借鉴生物免疫系统的抗体分子编码机理,在对样本进行参数估计情况下,提出熵度量单个特征对于目标和背景的识别敏感度从集合的角度研究并且定义了特征之间的包含和互补关系并且基于组成抗体分子氨基酸结合能量最小原则,提出了关于图像目标的免疫抗体构建规则最终实现了寻找最优特征子集的算法IACA ,该特征子集的维数通过算法自动获得无需人为设定,选择结果为目标的“免疫抗体”,能很好的从背景中识别目标. 利用归纳法证明了用IACA 得到的特征子集的最优性. 与其他特征选择方法比较,测试结果显示该算法具有较低的计算复杂度和错误识别率,表明了该方法的优越性和先进性.-Aiming at two classes image pattern recognition problem of object and background , a novel image feature selection method ,named immune antibody construction algorithm ( IACA) is proposed , inspired by the biological immune antibody encoding principle. In the case of sample parameter estimation , IACA considers entropy to measure individual feature’s sensitivity of object and background ,and defines the inclusion and complementary formulas about multi features in set theory perspective. Guided by the minimum energy principle , image immune antibody construction rules and corresponding algorithm are proposed to find an optimized feature subset as object immune antibody. Furthermore ,the dimension of the subset can be automatically determined with out prior setting. The induction proved the result was the optimal feature subset. Data testing result shows that IACA has a lower computational complexity and error recognition rate than other methods ,which has verified the superiority and t
Date : 2025-12-23 Size : 580kb User : 崔冰
[AI-NN-PR] Minimum-Energy-Consumption-Design- DL : 0: 本文介绍了一种在保证网络QOS需求（传输率）的前提下，对节点进行动态能量分配的中继选择算法。通过这种能量分配，减少了总的能量消耗，可以延长整个网络的生命周期。-For a given quality of service (QoS) requirement such as transmission rate between the source and the destination, relay nodes have an adaptive power control scheme to meet the QoS requirement. The adaptive power control scheme is assumed to be based on the channel condition between relay nodes and the destination. It is then an interesting problem to design an optimal relay network that minimizes total average energy consumption.
Date : 2025-12-23 Size : 103kb User : 苏红
[AI-NN-PR] GSAA DL : 0: 模拟退火算法来源于固体退火原理，将固体加温至充分高，再让其徐徐冷却，加温时，固体内部粒子随温升变为无序状，内能增大，而徐徐冷却时粒子渐趋有序，在每个温度都达到平衡态，最后在常温时达到基态，内能减为最小。根据Metropolis准则，粒子在温度T时趋于平衡的概率为e-ΔE/(kT)，其中E为温度T时的内能，ΔE为其改变量，k为Boltzmann常数。用固体退火模拟组合优化问题，将内能E模拟为目标函数值f，温度T演化成控制参数t，即得到解组合优化问题的模拟退火算法：由初始解i和控制参数初值t开始-Simulated annealing algorithm comes from solid annealing principle, will warm to fully solid high, then let it slowly cooling, heating, solid internal particles with a temperature rise of disorder, can increase, and gradually cooled gradually orderly particles, and in every temperature at the balance state, and the last in the normal temperature at the ground state, internal energy is reduced to the minimum standards according to the Metropolis, particle in temperature T tend to balance when the probability of e-Δ e/(kT), which for temperature T e the internal energy, Δ e for its change the volume, k as Boltzmann constant use solid annealing simulation combinatorial optimization problem, the internal energy e simulation for target function value f, temperature T evolution into control parameters T, namely get solution combinatorial optimization problem of simulated annealing algorithm: the initial solution I and control parameter optimization.finally T start
Date : 2025-12-23 Size : 5kb User : 黄
[AI-NN-PR] MoNiTuiHuoSuanFa DL : 0: 模拟退火算法来源于固体退火原理，将固体加温至充分高，再让其徐徐冷却，加温时，固体内部粒子随温升变为无序状，内能增大，而徐徐冷却时粒子渐趋有序，在每个温度都达到平衡态，最后在常温时达到基态，内能减为最小-Simulated annealing algorithm derived from solid annealing principle, the solid heated to a sufficiently high, let it slowly cooled, heated, the solid particles with the temperature rise becomes disordered state, internal energy increases, and slowly cooling particles gradually increasingly ordered, at each temperature has reached equilibrium, the final temperature reached in the ground state, which can be reduced to the minimum
Date : 2025-12-23 Size : 5kb User : icekwok
[AI-NN-PR] anneal DL : 0: 模拟退火算法来源于固体退火原理，是一种基于概率的算法，将固体加温至充分高，再让其徐徐冷却，加温时，固体内部粒子随温升变为无序状，内能增大，而徐徐冷却时粒子渐趋有序，在每个温度都达到平衡态，最后在常温时达到基态，内能减为最小-Simulated annealing algorithm derived solid Annealing is a probability-based algorithm, the solid is heated to a sufficiently high, and allowed to slowly cool down, when heated, the solid particles with the internal temperature becomes disordered shape, internal energy increases Great, while slowly cooling particles gradually orderly at each temperature has reached equilibrium, and finally reached the ground state at room temperature, can be reduced to a minimum within
Date : 2025-12-23 Size : 4kb User : 张洋