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.
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.
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.
DeepLearnToolbox-master
- 这是用于深度学习的Matlab工具箱 深度学习是机器学习的一个新的子领域,专注于学习深层次的数据模型。 它的灵感来自于人类大脑的明显的深层次(分层的)层次结构。 目录包括`NN /` - 一个用于前馈反向传播神经网络的库,`CNN /` - 卷积神经网络库,`SAE /` - 堆叠式自动编码器库,`CAE /` - 卷积自动编码器库,`util /` - 库使用的功能函数,`data /` - 实例使用的数据,`tests /` - 单元测试来验证工具箱是否正常工作(A Matlab to
GoogleNet_MATLAB-master
- GoogleNet 卷积神经网络 图片分类 分类精度高 网络结构深(GoogleNet convolution neural network image classification, high classification accuracy, network structure is deep)
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))
CNTK
- 在深度的重要性的驱使下,出现了一个新的问题:训练一个更好的网络是否和堆叠更多的层一样简单呢?解决这一问题的障碍便是困扰人们很久的梯度消失/梯度爆炸,这从一开始便阻碍了模型的收敛。归一初始化(normalized initialization)和中间归一化(intermediate normalization)在很大程度上解决了这一问题,它使得数十层的网络在反向传播的随机梯度下降(SGD)上能够收敛。 当深层网络能够收敛时,一个退化问题又出现了:随着网络深度的增加,准确率达到饱和(不足为奇)然后迅
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!)