搜索资源列表
C++200eg
- C++程序200个例子，其中从基础出发，由浅入深，很好的作为学习C＋＋的配套训练。-200 C Program, in which from the base, elementary, as a good learning C + + support training.
zhichixiangliangji.rar
- 支持向量积的调制识别原代码，关于学习训练,Support Vector plot of the original code modulation recognition, Learn about the training
中文分词算法
- 本程序使用给出的字典进行学习并对训练语料进行分词处理，采用C语言编写，高效易懂！
gmmem_several
- GMM是语音识别中比较成熟的算法之一，这个MATALB完整的实现了基于GMM算法的识别训练程序，可以适用于GMM识别和学习的同行的参考-GMM is a speech recognition algorithm for the more mature one, this MATALB full implementation of the identification algorithm based on GMM training procedures, can be applied to GMM
duojishilianglbgvq
- 对于语音编码参数的有权重多级矢量量化，主要是对LSP码本训练，这个权重学习语音的都应知道，且这个可以训练大的语音参数，完全自已写的。上传前已调试成功。-Speech coding parameters for the right to re-multistage vector quantization, mainly for LSP codebook training, the right to re-learn voice should know, and that this can be t
memo
- 该程序为作者的第四个MEMO控件的程序它介绍了如何学习编简单的打字训练软件-The program for the fourth author MEMO control procedure describes how to study it for a simple typing training software
hmm
- hmm语音识别程序，能根据参数，训练模型和计算出模型距离，对于学习和编写有关隐马尔科夫语音识别程序很有帮助-hmm speaker recognition program，use it you can directly write an hmm program easly.
bianyiyuanli
- 编译原理，老师讲课的ppt 很全面 值得很好学习-Compiler Construction Principles, teachers lecture ppt very comprehensive study should be very good
BP1
- 这是BP神经网络的matlab代码，调节对学习速率、隐含层数等不同参数的设置，通过神经网络的不断训练，观察图形，以得到最好的拟合-This is for us green hands.BP shen jing wangluo xuyao dui gezhong canshu jinxing butong de xunlian,yi dadao zuiyou nihe.
spams_2.3
- 字典学习 和 矩阵分解的工具箱，用于训练数据。-SPAMS: a SPArse Modeling Software
Handwritten-numeral-recognition
- 为了实现对手写字体的识别，运用了人工智能的分层神经网络思想，对识别的字体通过训练学习，达到识别手写字体的功能。-to realize the recognition of handwritten font, using hierarchical neural network artificial intelligence, to identify fonts through training and learning, to identify the handwriting function.
maxent
- 运用最大熵对一个文本中的类进行训练模型，然后可用模型进行预测，结果返回类名，是机器学习语言的重要部分，支持汉字分类-Use of maximum entropy of a text in class training model, the model can then be used to predict the results returned class name is an important part of machine learning languages, support for
xiaoxuesuxue
- 一个用于幼儿、小学数学训练的趣味软件。可以大大提高孩子的学习效果。-This software is used for child care, elementary school mathematics training fun software. Can greatly improve a child s learning.
elm2
- 极限学习机（Extreme Learning Machine，ELM），该算法随机产生输入层与隐含层间的连接权值及隐含层神经元的阈值，且在训练过程中无需调整，只需要设置隐含层神经元的个数，便可以获得唯一的最优解。与传统的训练方法相比，该方法具有学习速度快、泛化性能好等优点-Extreme Learning Machine regression and classification, introduce a new algorithm for SLFN- Extreme Learning Mach
image-segment
- 这是用ELM（极限学习机）做的关于图像识别的分类实验，有数据，有程序，有训练时间，测试时间和精度-It is used ELM (Extreme Learning Machine) to do experiments on the classification of image recognition, has data, procedures, training time, test time and accuracy
CNTKBook-Draft0.4-2015-01-04
- 语音识别中深度学习模型的训练工具，可以用于研究工作。-DNN for ASR
MPIch-KNN
- 基于MPICH的KNN并行化计算，固定5个进程同时计算，经24W个训练样本学习，预测效果良好.-MPICH-based KNN parallel computing, fixed five processes simultaneously calculated by 24W training samples to learn, good prediction.
HMM_EM
- Hadoop隐马尔科夫模型的实现，有训练算法（EM）,产生的模型参数可以用来单机使用，亲测可用，可供正在学习hadoop的同学参考-Implement Hadoop hidden Markov model, there are training algorithm (EM), the model parameters can be used to produce stand-alone use, pro-test available for reference students are lear
frft
- 基于统计特征的语种识别算法分析与实现。1.提取语音的客观统计特征；2、通过分类器建立训练学习模型；3、将模型运用于汉语、英语、日语等语种识别实验，与人的主观感觉做对比-Based on statistical language identification algorithm analysis and Realization of objective statistics. The extraction of speech features 2, the classifier built th
shiyan1
- 利用多GPU进行分布式训练,用的是tensorflow的Keras平台(Distributed Training Using Multi-GPU)