Location:
Search - neural pruning
Search list
Description: This function applies the Optimal Brain Surgeon (OBS) strategy for
％ pruning neural network models of dynamic systems. That is networks
％ trained by NNARX, NNOE, NNARMAX1, NNARMAX2, or their recursive
％ counterparts.-This function applies the Optimal Brain Surgeon (OBS) strategy for pruning neural network models of dynamic systems. That is networks trained by NNARX, NNOE, NNARMAX1, NNARMAX2, or their recursive counterparts.
Platform: |
Size: 5120 |
Author: 张镇 |
Hits:
Description: 这是《精通VC++数字图像模式识别技术及工程实践[第2版]》光盘源代码，其中包括EM算法、fisher判别函数、HMM隐马尔科夫模型、BP神经网络、小波变换、alpha-beta剪枝、A*算法等，还包含几个纹理分析、人脸定位、字符识别、车牌号识别、8数码、黑白棋、离线/在线签名等实例，因此对于学习模式识别、人工智能的朋友们都大有裨益。光盘中的素材请见另外一个资源。-This is " proficient in VC++ Digital Image Pattern Recognition Technology and Engineering Practice [2nd edition]" CD-ROM source code, including the EM algorithm, fisher discriminant function, HMM hidden Markov model, BP neural network, wavelet transform, alpha- beta pruning, A* algorithm, but also contains a number of texture analysis, face positioning, character recognition, license plate number recognition, digital 8, Reversi, offline/online signatures examples, so for studying pattern recognition, artificial intelligence friends are of great benefit. CD-ROM material, see the other resources.
Platform: |
Size: 14680064 |
Author: 吴 |
Hits:
Description: 这是神经网络里面结构优化里面重要的剪枝方法之一，灵敏度剪枝方法。-This is a neural network structure optimization inside one of the methods inside the major pruning, sensitivity pruning method.
Platform: |
Size: 2048 |
Author: 赵寿玲 |
Hits:
Description: 基于VC++的神经网络剪枝算法程序；“剪枝算法”是一种通过简化神经网络结构来避免网络过拟合的有效方法之一。内附程序说明文档，介绍了该算法的主要原理，运行结果说明以及程序流程图。是很好的学习资料-VC++ based on neural network pruning algorithm program " pruning algorithm" is a kind of neural networks by simplifying the network architecture to avoid over-fitting of the effective methods. Containing a description of the procedures document, describes the main principles of the algorithm, running results show and program flow chart. Is a very good learning materials
Platform: |
Size: 230400 |
Author: xinxin |
Hits:
Description: 神经元网络结构优化和调整的剪枝算法程序源码（附带中文解释）-Neural network pruning algorithm optimization and adjustment of program source code (with Chinese interpretation)
Platform: |
Size: 1024 |
Author: fo |
Hits:
Description: 经典的黑白棋游戏，其中设计并实现了多种黑白棋的人工智能算法，其中使用了BP神经网、决策树、优化启发搜索剪枝等算法。并实现了多种算法对战平台，进行算法间的对弈和比分统计，以供进一步研究黑白棋算法。其中，该系统中的高智能算法已经在同类黑白棋软件的棋力中占上游水平。-Classic black and white chess game, in which artificial intelligence algorithm of many kinds of Othello was proposed and implemented, including the use of the BP neural network, decision tree, heuristic search pruning algorithm. And to achieve a variety of algorithms of battle platform, through the game and score statistic algorithm, for further study of Othello algorithm. Among them, high intelligent algorithm in the system has been accounted for the upper level in the same software in Othello chess.
Platform: |
Size: 5278720 |
Author: 舒愈 |
Hits:
Description: 用Skeletonization剪枝方法精简BP神经网络结构，提高网络泛化能力，对手写数字进行识别。-Skeletonization pruning method using BP neural network architecture to streamline and improve the network generalization ability of the handwritten digits recognition.
Platform: |
Size: 175104 |
Author: 屠海斌 |
Hits:
Description: 用神经网络，α-β剪枝以及进化算法实现五道棋程序的智能。Java编写，没有添加界面部分，仅仅是控制台上的程序。-Neural network, α-β pruning and evolutionary algorithms five Dao intelligent program. Written in Java, do not add the interface part, merely procedural console.
Platform: |
Size: 2787328 |
Author: 梁惠源 |
Hits:
Description: 实现了四子棋的功能，由Java编写，有界面部分，运用了神经网络、进化算法、剪枝算法-To achieve a four-game features, written by Java, there is part of the interface, the use of neural networks, evolutionary algorithms, pruning algorithm
Platform: |
Size: 4423680 |
Author: 梁惠源 |
Hits:
Description: We introduce Dynamic Deep Neural Networks (D2NN),
a new type of feed-forward deep neural network that allows
selective execution. Given an input, only a subset of D2NN
neurons are executed, and the particular subset is determined
by the D2NN itself. By pruning unnecessary computation
depending on input, D2NNs provide a way to improve
computational efficiency. To achieve dynamic selective
execution, a D2NN augments a feed-forward deep neural
network (directed acyclic graph of differentiable modules)
with controller modules. Each controller module is
a sub-network whose output is a decision that controls
whether other modules can execute.
Platform: |
Size: 1318912 |
Author: nextwang |
Hits: