-
一种新的ica算法，主要是应用与盲分离算法，大家可以
一种新的ica算法，主要是应用与盲分离算法，大家可以-ica a new algorithm, and are primarily used to blind separation algorithm, we can s
- 2023-05-26 11:35:03下载
- 积分：1
-
人脸检测定位的示例代码.rar VC++源码，具有一定参考价值,我也是从别处下载下来的。...
人脸检测定位的示例代码.rar VC++源码，具有一定参考价值,我也是从别处下载下来的。-Face Detection positioning the sample code. Rar VC source, which have a certain value, I also downloaded from the elsewhere.
- 2022-02-13 01:34:33下载
- 积分：1
-
基于遗传算法的多移动机器人协调路径规划，这是国内的专家篆写的文章。我觉得写得不错，推荐给大家看看。...
基于遗传算法的多移动机器人协调路径规划，这是国内的专家篆写的文章。我觉得写得不错，推荐给大家看看。-based on genetic algorithms more mobile robot path planning coordination, which is the domestic experts Fragrance write articles. I think well-written and recommend it to see.
- 2022-04-07 22:28:16下载
- 积分：1
-
各种神经网络C源代码。包括： CPN、BPN、ART1、ART2。
各种神经网络C源代码。包括： CPN、BPN、ART1、ART2。-various neural network C source code. Include : CPN, 7.82, ART1, ART2.
- 2022-05-15 16:59:56下载
- 积分：1
-
经典的BNP神经网络例子
经典的BNP神经网络例子-classic example BNP neural network
- 2022-02-22 02:44:42下载
- 积分：1
-
Common ant colony algorithm, this algorithm can efficiently solve the problem ts...
通用的蚁群算法，这个算法可以高效地解决tsp问题-Common ant colony algorithm, this algorithm can efficiently solve the problem tsp
- 2023-08-08 13:10:03下载
- 积分：1
-
模式识别中的常用搜索算法中的8数码游戏程序
模式识别中的常用搜索算法中的8数码游戏程序-pattern recognition of commonly used search algorithm of eight digital Games
- 2022-01-25 23:15:19下载
- 积分：1
-
运用比例共轭梯度动量算法来训练BP网络并对机械振动峰峰值进行预测。...
运用比例共轭梯度动量算法来训练BP网络并对机械振动峰峰值进行预测。-use ratio conjugate gradient algorithm to train the momentum BP also peak of mechanical vibration prediction.
- 2022-01-24 10:21:43下载
- 积分：1
-
用三层BP网来进行函数逼进，语言是VB6.0编写
用三层BP网来进行函数逼进，语言是VB6.0编写-BP network with the three-tier to function pressing language is prepared VB6.0
- 2023-07-16 19:50:04下载
- 积分：1
-
包含2个源代码，这是一个源程序的源程序，和O的..
内附两个源代码，其中一个源代码是识别程序的，另一个是一个矩阵类库的，所以一并附上。
~..~因为已经保存了训练好的网络权值，所以第一次使用识别程序时，可以直接运行Release目录下的可执行文件，然后对图片目录中的测试图片进行读入、识别。
当然读者也可以自行用训练样本训练网络，不过要特别注意训练样本的选择，否则可能造成识别率很低。训练样本选择的原则是，尽可能的有代表性，在训练时间不至于太长的情况下，训练样本数目尽量多。 -containing 2 source code, which is a source identification procedures, and the other is a matrix class library. So accompanied. ~ ~ .. Has been preserved because of the trained network weights, the first use of the identification procedures, can be run directly Release directory executable file, Then the catalog of tests conducted read into the picture, recognition. Certainly readers can use their own training samples training network, but special attention should be paid to the choice of training samples, Otherwise, it could cause a very low recognition rate. Training sample selection principle is that as far as possible be representative, in the training of the time not too long under the circumstances, the number of training samples as much as possible.
- 2022-08-11 21:14:16下载
- 积分：1
