搜索资源列表
Deep-Learning-Note
- 对学习深度神经网络很有用的资料，深入浅出地对相关的知识点进行了解析，值得一阅-Very useful for learning neural network, explain profound theories in simple language to analyze the related knowledge points, worth reading
DeepLearningTutorials-python
- 深度神经网络轻量级工具包，Python简单实现，内含各种模型的代码以及模型的简单理解说明，适合初学者阅读使用。-Deep Neural Networks lightweight toolkit, Python simple implementation, containing simple to understand explanation of each model and the model code, suitable for beginners read.
DeepNeuralNetwork20150129
- matlab code for Deep Neural Network
neural-network
- 深度学习python实现，并附有MNIST上的测试程序，准确率98 以上-Deep learning learns low and high-level features large amounts of unlabeled data, improving classification on different, labeled, datasets. Deep learning can achieve an accuracy of 98 on the MNIST dataset.
matlab-Deep-Learn
- MATLAB神经网络经典程序 包括多个神经网络程序、深度学习程序-MATLAB neural network program including mutil network and deep learning program
Neural-Networks-and-Deep-Learning
- 很好的深度学习与神经网络教程，适合深度学习的初学者-Good depth and neural network learning tutorial for beginners to learn the depth of
DNN_toolbox
- 语音分离用的深度神经网络工具箱，matlab，非常全 -This folder contains Matlab programs for a toolbox for supervised speech separation using deep neural networks (DNNs).
VGG-16
- 深度神经网络VGG-16模型的keras代码，用于图像识别-keras codes of deep neural network VGG-16 model, used of image classification
Artificial-Neural-Networks
- 深度学习，人工神经网络的模型，逐层学习算法，可以构建多层的-deep learning, artificial neural network model, learning algorithm, can construct a multi-layer
CNN
- 卷积神经网络是一种特殊的深层的神经网络模型，它的特殊性体现在两个方面，一方面它的神经元间的连接是非全连接的， 另一方面同一层中某些神经元之间的连接的权重是共享的（即相同的）。它的非全连接和权值共享的网络结构使之更类似于生物 神经网络，降低了网络模型的复杂度（对于很难学习的深层结构来说，这是非常重要的），减少了权值的数量。-Convolution neural network is a kind of special deep neural network model, its particula
nature-deep-learning
- 世界顶级杂志《自然》，针对人工智能的深度学习进行的最全面综合论述，以及对未来深度学习及神经网络的发展预测，值得一读！-The world s top magazine nature , for the depth of artificial intelligence to learn the most comprehensive exposition, as well as the future development of deep learning and neural network p
CNN
- CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Deep Neural Network It provides deep learning tools of deep belief networks (DBNs). myCNN is a Matlab implementation
deep-learning
- 深度学习主要通过人工神经网络的思想发现数据的分布式特征表示-Deep learning discovers the distributed representation through artificial neural network.
neural-networks-and-deep-learning-master
- 用不同的方法实现了神经网络（没有用第三方库，就是用numpy等实现的，对于初学者来说是不错的深入了解神经网络的素材）(Using different methods to achieve the neural network (not using third square libraries, that is, using numpy and so on, for beginners is a good understanding of the neural network material))
neural-networks-and-deep-learning-master
- neural-networks-and-deep-learning-master
Learning Deep Architectures for AI
- 一本关于深度架构学习算法，尤其是用来构造更深层模型的非监督学习的单层模型。(Theoretical results suggest that in order to learn the kind of com- plicated functions that can represent high-level abstractions (e.g., in vision, language, and other AI-level tasks), one may need deep archite
Deep Learning Based Communication Over the Air
- 通信系统的端到端学习是a 引人入胜的新颖概念迄今为止仅被验证 模拟基于块的传输。它允许学习 发射机和接收机实现为深度神经网络 （NN），它们针对任意可区分的端到端进行了优化 performancemetric，例如块错误率（BLER）。在本文中，我们 证明无线传输是可能的：我们建造， 训练，并运行完整的通讯系统 的神经网络使用非同步的现成软件定义无线电 和开源深度学习软件库。(End-to-end learning of communications systems is a
py3-neural-network-master
- Python3.6实现神经网络算法，经过mnist数据集测试后表现良好，准确率约为95%-96%。 /src 为源代码 /data为mnist算集(This is a code samples for "Neural Networks and Deep Learning" using python3.)
cifar10_tutorial
- 非常适合入门的一个深度学习图片分类例程！(Very suitable for beginners to learn a deep picture classification routines!)
Deep Neural Network
- 深度神经网络训练过程中：首先是进行初始化，根据需求设置神经网络的基本结构；然后进行前向传递（feedforward），层与层之间进行传递，求得误差；然后进行反向传播（back propogation），根据误差最小化原则，使用随机梯度下降法，对各个参数进行求导，确定下降方向，对各个参数进行更新(In the training process of deep neural network, firstly, initialization is carried out, and the basic