搜索资源列表
matlab
- 利用一个单隐层BP网络来逼近一个函数，在改程序中有21组数据。该网络的输入层和输出层的神经元个数均为一。-Using a single hidden layer BP network to approximate a function, in the reform process there were 21 sets of data. The network input layer and output layer are a number of neurons.
izh_single_neuron_tonic_RK
- It can be used in simulating izhikevich neurons
understanding_and_applying_machine_vision_0824789
- Perhaps because no important information is represented in absolute brightness values in the visual environment, the visual system has confined its processing almost exclusively to differences – spatial and temporal contrasts. Recording from ne
2-different-neurons(1)
- 对于两个不同神经元进行耦合后的体系进行模拟-Simulated for two different neurons coupled system
NEROPID1
- 控制领域中单神经元的实现，通过对外提供三个接口可实现个参数的直观访问与应用-Realization of single neurons in the control area by providing intuitive access and application of the three interfaces can be achieved parameters
izhikevichneurals
- 1000个神经元进行耦合，兴奋性神经元和抑制性神经元比例为四比一，绘出了它们的活动。-The 1000 neurons coupled excitatory neurons and inhibitory neurons in a ratio of four to one, draw their activities.
BP-network
- 掌握用BP网络解决实际预测问题的方法，包括数据规格化处理、训练样本和测试样本的组织，网络隐层层数和神经元个数的确定，以及传递函数和训练参数的确定等。-Mastered the method of BP network to solve practical prediction problems, including the normalized data processing, training samples and test samples of tissue, the number of
LIF_count
- Leaky intergration model，神经元里比较简单的模型。计算在一定时间内发放的次数-Leaky intergration model, a relatively simple model neurons. Calculating the number of payment within a certain time
Neural-network-algorithm
- 人工神经网络就是模拟人思维的第二种方式。这是一个非线性动力学系统，其特色在于信息的分布式存储和并行协同处理。虽然单个神经元的结构极其简单，功能有限，但大量神经元构成的网络系统所能实现的行为却是极其丰富多彩的。-Artificial neural network is the second way to simulate human thinking. This is a nonlinear dynamical system, which feature information distribut
NN_Task1
- 建立一个bp神经网络解决异或问题：神经网络的结构采用2:2:1的结构，可以改变隐层神经元的个数。-Create a bp neural network to solve XOR problem: the structure of the neural network structure using 2:2:1, you can change the number of hidden layer neurons.
123
- 利用三层BP神经网络来完成非线性函数的逼近任务，其中隐层神经元个数为五个。-To complete the task of nonlinear function approximation by three layers of BP neural network, in which the number of hidden layer neurons into five.
yinhancengjiddianshu
- 将下载后的.m文件和.fig文件放在同一个路径下，运行，填写好输入输出节点数。就可以得到初始隐含层神经元的节点数。-And will download. After m file. FIG file on the same path, running, fill out the number of input and output nodes. You can get the initial number of nodes in the hidden layer neurons.
offline-signature-recognition
- As signatures are widely accepted bio-metric for authentication and identification of a person because every person has a distinct signature with its specific behavioral property, so it is very much necessary to prove the authenticity of signature
HHT
- 把HHT和神经网络结合起来，识别出是否故障。对于HHT变换，这里用到的是它的IMF分解，然后用能量理论来判别哪些模组是虚假分量，哪些是是真实分量。对于EMD分解后的谱进行特征提取 ，利用的理论基础就是模糊熵。计算出真实 分量的模糊熵，作为输入层；输出层为两个神经元，为0（故障 ）1（正常 （正常 ）判别该信号是否出现故障。-The combination of HHT and neural network to identify whether the fault. For the HHT tr
47821364121
- 根据果蝇优化算法得到极速学习机隐层神经元的数目依据得到的隐层神经元数目和极限学习机的方法对训练样本和测试样本进行训练学习。-According to the fruit flies optimization algorithm to get extreme learning machine based on the number of hidden layer neurons of hidden layer neurons number and extreme learning machine
anymin
- 本程序使用GMDH网络对交通的流量进行预测，输入的数据为连续n天的m组流量数据。 输出数据为第n+1天的m组的流量的预测数据。 每个神经元的学习方式为widrow-hoff 在学习过程中，每一层否挑选15个优秀的神经元保留到下一层(This procedure uses GMDH network traffic flow prediction, the input data for the continuous n days of M group traffic data. The ou
Redes Neurais Artificiais
- It is a parallel distributed processor made up of simple processing units, which have the natural propensity to store experimental knowledge and make it available for use. It resembles the brain in two respects: 1. The knowledge acquired by the netw
Untitled
- 建立BP神经网络， 12个隐层神经元，4个输出神经元 tranferFcn属性 'logsig' 隐层采用Sigmoid传输函数 tranferFcn属性 'logsig' 输出层采用Sigmoid传输函数 trainFcn属性 'traingdx' 自适应调整学习速率附加动量因子梯度下降反向传播算法训练函数 learn属性 'learngdm' 附加动量因子的梯度下降学习函数(The BP neural network is established, with 12 hidden la
organisation_fonctionnelle_MT_deangelis_99
- Neurons selective for binocular disparity are found in a number of visual cortical areas in primates, but there is little evidence that any of these areas are specialized for disparity processing. We have examined the organization of disparity-sel
reu_paper_formatted
- Neurons in the visual cortex develop receptive fields that are sensitive to oriented features in the visual environment. However, exactly how these features develop in a self-organizing way, and how the brain learns to recognize what orientation is r