搜索资源列表
FaceRecognitionBased-OnDeepLearning
- 本文运用深度神经网络的方法克服姿态变量和图像分辨率的影响,提出了一种多姿态的人脸超分辨识别算法并在实验数据集上获得了良好的性能表现。另外本文利用深度信念网络探索正面人脸图像和侧面人脸图像的映射,方法放松了深度信念网络的输入也输出之间绝对相等,而只是保证其高层含义上的相等。实验表明了使用深度信念网络可以学习到侧面人脸图像到正面人脸图像的一个全局映射,但是丢失了个体细节差异。本文还提出了基于深度网络保持姿态邻域进行姿态分类的方法,在学习过程中,我们保证了同一个姿态下的人脸图像应该与同一姿态下的多张图
propagation-algorithm-BSC-channel
- Belief propagation algorithm over the BSC channel
evaluating-data-reliability
- There are many available methods to integrate information source reliability in an uncertainty representation, but there are only a few works focusing on the problem of evaluating this reliability. However, data reliability and confidence are essenti
decoder_BP_SE_ref
- 置信传播即BP译码算法，在每一次迭代过程中,都要对全部比特和校验信息进行更新,存在计算量大、译码效率低的问题,故提出了单边传播信息的迭代BP算法-Belief Propagation that BP decoding algorithm, in each iteration, we must check for all the bits and update the information, there is a large amount of calculation, low coding e
decoder_BPML
- 置信传播(belief propagation,BP)算法的计算复杂度较高，且变量节点和校验节点间信息传递的信息可靠，但是迭代的实现，就最大似然算法来说，验证其提高译码性能的特点。 -Belief propagation (belief propagation, BP) higher computational complexity of the algorithm, and reliable information between variable nodes and check node
decoder_BP_MRF
- 将置信传播(belief propagation,BP)算法从马尔科夫随机域的角度进行理解， 并通过变量节点和校验界定之间的迭代来实现信息传递，进而提高系统的误码率性能。 -The belief propagation (belief propagation, BP) algorithm is understood from the perspective of Markov random field, and by defining the iteration variable nod
decoder_BP_CPE
- 置信传播是一中很有效的算法，将其应用于检测，通过在检测与译码之间迭代交换传递信息，并有选择地通过单边消息传递来更新信息，降低系统实现的复杂度。 -Belief propagation is a very efficient algorithm to be applied to the detection, the information transmitted by the exchange between the iterative detection and decoding, and to
decoder_BP_EB
- 通过单边选择实现低复杂度的置信传播（BP）算法，并将此算法应用于检查模型中，可有效提高系统的性能，且具有较低的复杂度-Select achieved through unilateral low-complexity belief propagation (BP) algorithm, and the algorithm is applied to check the model can effectively improve system performance, and has lower
decoder_BP_MMSE_CPE
- 置信传播算法可通过因子图的角度理解，也可通过马尔科夫随机域的思想来理解，不管从哪个角度实现，都可将其应用于检测，提高性能。-Belief propagation algorithm can be understood by the angle factor graph can also be understood by thinking of Markov random field, regardless of the angle from which to achieve, can be ap
QPSK
- QPSK经格雷码优化后过调制解调后的误码率误信率判决-After QPSK Gray code optimization via modem error rate over the mistaken belief that the rate of post-judgment
JavaBPForMatlab
- 置信传播算法的实现代码，用JAVA和Matlab结合的方法实现，在Matlab中可以调用Java实现的程序。-Code for belief propagation. It employs the programming language of Java and Matlab.
Polar-Codes-New
- 关于polar 码的SC（Successive Cancellation）译码程序，与原作者用BP（belief propagation）实现的译码程序“Polar code encoder and decoder”可以对比看-This is a SC decoding program about polar codes
MRF1.6
- This directory contains the MRF energy minimization software accompanying the paper [1] A Comparative Study of Energy Minimization Methods for Markov Random Fields. R. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarw
efficient_belief_prop.tar
- a C++ implementation of the stereo and image restoration algorithms described in the paper: Efficient Belief Propagation for Early Vision Pedro F. Felzenszwalb and Daniel P. Huttenlocher International Journal of Computer Vision, Vol. 70, No
llr_pearl
- 低密度奇偶校验码的最大似然译码的置信度传播算法-Belief-propagation decoding algorithm: Log-likelihood domain
pearl
- 这是最稳定的BP译码方式，就数值精度来说的话。-Belief-propagation decoding algorithm: Probabilistic decoding The algorithm works directly with probabilities. In terms of numerical precision, it is the most stable BP decoder, although it is very intensive in terms of exp()
Deep-Learning-Toolbox
- 深度学习matlab工具箱,包括深度deep belief nets,stacked autoencoder,convolutional neural nets等网络。-Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Ne
cc
- 系统地综述了基于MRF的图像分割方法。介绍了基于MRF模型的图像分割理论框架,给出了当前MRF图像建模研究的热点问题。概括了基于MRF模型的图像分割算法,包括图割算法、归一化割算法、置信度传播算法等,指出了这些算法的发展方向-Summarized the image segmentation method based on MRF. Introduces the image segmentation based on MRF model theory framework, gives the h
DeepLearnToolbox-master
- 深度学习如深度置信网重构误差及迭代时间实验，里面含有数据库-Depth of learning such as deep belief network reconstruction error and iteration time experiment, which contains the
crbm_audio_r2
- cdbn.卷积深度信念网络用于声音识别。此代码为老外写的matlab代码-Cdbn. convolutional depth belief network for identification of sound. This code for a foreigner to write matlab code Cdbn. convolutional depth belief network for identification of sound. This code for a foreigne