资源列表
Genetic-algorithm-optimization
- 遗传算法优化B P神经网络的目的是通过遗传算法得到更好的网络初始权值和阈值, 其 基本思想就是用个体代表网络的初始权值和阈值、 个体值初始化的B P神经网络的预测误差作为该个体的适应度值, 通过选择、 交叉、 变异操作寻找最优个体, 即最优的B P神经网络初始权值。除了遗传算法之外, 还可以采用粒子群算法、 蚁群算法等优化B P神经网络初始权值。-Genetic algorithm to optimize BP neural network is designed by means of g
fastslam
- 压缩扩展卡尔曼滤波的同时定位与构图算法，自行设定路径和路标，动画显示定位过程-Compression and expansion of Calman filter simultaneous localization and mapping algorithm, set the path and road signs, animation display positioning process
PSO-for-BP
- 用粒子群算法来训练网络参数，直到误差趋于一稳定值，然后用优化的权值用于BP算法-PSO is used to optimize connection weights of forward-back neural network until the learning error has tended to stability, Then we use BP algorithm with optimized weights to finish short-term load forecasting
chapter3
- 图像处理 人工智能 神经网络 深度学习 数值计算(picture process artificial intelligence bp numberical calculation)
ompbox
- K-SVD算法用于稀疏表达，基于OMP算法。(The algorithm is apply for the sparse representation.)
BP
- bp神经网络，包含输入层，隐含层，输出层(BP neural network, including the input layer, the hidden layer, the output layer)
语音识别
- 语音识别例子，使用windows平台，visual studio13 开发。(speech recognition windows visual studio13)
phoby
- 采用粒子算法实现的模拟火焰燃烧的效果,程序比较简单,很容易明白()
asymc
- cfd源程序,编程时能直接或参考的程序,C语言()
HW7-1
- 自编码器显示minst数据集中重构误差最大的十幅图片(Self-encoder shows ten images with the largest reconstruction error in the minst data set)
matlab
- pn结模拟：一维PN结的模拟 ，有限元法 结合耦合法，新手求交流(Pn junction simulation: one-dimensional pn junction simulation, finite element method combined with coupling method, novice for communication)