搜索资源列表
paper1
- A Comparative Evaluation of Deep Belief Nets in Semi-supervised Learning
paper2
- A fast learning algorithm for deep belief nets
deepnet-master
- Nitish Srivastava University of Toronto.利用GPU训练深度学习算法-Implementation of some deep learning algorithms. Nitish Srivastava University of Toronto. GPU-based python implementation of 1. Feed-forward Neural Nets 2. Restricted Boltzmann Machines
an_malli_ajo1
- Contrary to popular belief, Lorem Ipsum is not simply random text. It has roots in a piece of classical Latin literature 45 BC, making it over 2000 years old. Richard McClintock-Contrary to popular belief, Lorem Ipsum is not simply random text. It ha
adaptive-learning
- 一篇关于深度网络的改进算法的文章,主要是采用了一种动态权值的调整机制-Towards adaptive learning with improved convergence of deep belief networks on graphics processing units.pdf
PAPER1
- Acoustic modeling using deep belief networks
paper2
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
LDPC
- Parity check bits is computed using sparse LU decomposition, utilizing sparse matrix properties of H. LDPC code decoding is done using iterative belief propagation or sum-product algorithm (SPA). Four versions of SPA decoder are presented.
New-Iterative-Decoding-Algorithms-for-Low-Density
- Low-Density Parity-Check (LDPC) codes have gained lots of popularity due to their capacity achieving/approaching property. This work studies the iterative decoding also known as message-passing algorithms applied to LDPC codes. Belief propagation
Semiconductor-Basics
- Materials can be categorized into conductors , semiconductors or insulators by their ability to conduct electricity. It is a popular belief that insulators do not conduct electricity because their valence electrons are not free to wander throughout t
DeepLearnToolbox-master
- 这是深度学习的常用工具箱,里面包括常用的自动编码器、卷积神经网络和深度置信网络的函数- This is a common toolbox depth study, which includes functions commonly used automatic encoder, convolutional neural network and depth of belief networks
PG_DEEP-master
- A fast learning algorithm for deep belief nets 文章代码-2006 A fast learning algorithm for deep belief nets
Sparse-Autoencoder
- 稀疏编码算法是一种无监督学习方法,它用来寻找一组“超完备”基向量来更高效地表示样本数据-2006 A fast learning algorithm for deep belief nets
DBN
- 深度信念网络 (Deep Belief Network, DBN) 由 Geoffrey Hinton 在 2006 年提出。它是一种生成模型,通过训练其神经元间的权重,我们可以让整个神经网络按照最大概率来生成训练数据。我们不仅可以使用 DBN 识别特征、分类数据,还可以用它来生成数据。下面的图片展示的是用 DBN 识别手写数字: -Depth belief networks (Deep Belief Network, DBN) proposed by the Geoffrey Hinton i
ldpc_decode
- ldpc译码程序,基于MATLAB,采用置信传播算法-LDPC decoding process, based on MATLAB, using the belief propagation algorithm
DeepLearnToolbox
- DeepLearnToolbox是Matlab的深度学习工具箱,包含了深度信度网络DBN,卷积网络CNN,SAE(stacked auto-encoders),CAE(Convolutional auto-encoders)和NN深度学习算法的实现。-DeepLearnToolbox is a MATLAB toolbox about depth learning, contains realizations of deep belief network DBN, convolutional n
DBN
- 深度学习的深度信念网的C++源代码,开源的源代码-Depth study of the depth of the belief network C++ source code
matlab
- 使用的版本:64位的MATLAB R2015b,代码可以直接运行仿真。 (1)提取五个特征量中的Hu矩和仿射不变矩; (2)picture用来存放训练样本和测试样本; (3)save用来保存代码运行过程中提取的特征量,matlab1存放仿射不变矩特征量, matlab2存放Hu矩特征量,Hu_BBA存放样本的Hu矩的基本信度赋值和识别类型, FS_BBA存放样本的仿射不变矩的基本信度赋值和识别类型,目标识别矩阵、信息融 果和判决结果在指令窗输出(1,2,3表示类型,
Facial_Feature_Tracking
- 通过建议一个人脸形状先验模型关注该问题,该模型基于受限Boltzmann Machines (RBM)及其变种构建。特别的,我们首先基于深度信任网络构建一个模型以获取接近正视角的表情变化的人脸形状变量。为了解决姿态变化问题,我们将正面人脸形状先验模型整合到一个3路(3-way)RBM模型,其可以获取正面人脸形状和非正面人脸形状间的关系。最后,我们建议一个方法,将人脸先验模型和人脸特征点的图像度量系统性地组合在一起。-we address this problem by proposing a
dbn-master
- Codes related with tutorial: *Data modeling: deep belief networks*. Getting Started - Presentation - https://docs.google.com/presentation/d/1wZ8Mx6q3H-gwZh-lJWBQFPUmuhSZWwNp5QYxLBW4v5U- Codes related with tutorial: *Data modeling: deep be