搜索资源列表
Learning-hierarchical-invariant
- deep learning一般是学习的层次结构，它也是有一定理论依据的，即模拟人脑的大脑皮层工作，因为大脑皮层的视觉区域也是分层次工作的，越底层的视觉皮层对那些底层特征就越敏感。综上所述，feature learning有这么多应用需求的驱动和生物神经理论上的支持，注定它能够在AI领域中发挥一定的作用。一些实验表明，有些feature learning学习到的特征几乎比所有其它的特征效果要好，比如本文中的ISA模型就是其中一个。-deep learning hierarchy of learni
deep-Learning
- 实现常见的深度神经网络的学习过程，适合初学者学习使用，也可以进一步开发使用，具有较高的学习价值和学术价值。-The depth to achieve common neural network learning process, suitable for beginners to learn to use, can be further developed to use, with high learning and academic values.
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
paper1
- Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
deepLearnToolbox-master
- 深度学习工具包，包含神经网络，卷积神经网络等众多深度学习工具的MATLAB源码-MATLAB source deep learning kits, including neural networks, neural networks, and many other convolution depth learning tool
neural-style-master
- 深度学习 艺术画风的学习。Linux下torch编译工具进行运行。-deep learning neural-style
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
FractalNet
- 2016年6月刚刚出来的运用分形网络的深度神经网络的牛文，值得学习，欢迎大家交流。-June 2016 Niu just out of the fractal network of deep neural networks, it is worth learning, we welcome the exchange.
2015-LiYuming-IQA
- LiYuming2015年在Neurocomputing发表的基于剪切变换和深层神经网络的无参考图像质量评价的文章源码及论文No-reference image quality assessment with shearlet transform and deep neural networks-No-reference image quality assessment with shearlet transform and deep neural networks
prnaussia
- In this paper, we propose deep transfer learning for classification of Gaussian networks with time-delayed regulations. To ensure robust signaling, most real world problems from related domains have inherent alternate pathways that can be learned
MSCNN_dehazing2016
- 通过CNN计算大气散射模型中的传播率，从而实现图像去雾-multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps
SAE_DBN_CNNToolbox
- 多种深度学习框架，主要包括堆栈稀疏自动编码器，深信度网络，卷积神经网络等。对于灰度图像和高维图像，展现非常强大的学习性能。-A variety of deep learning framework, including automatic stack sparse encoder, is convinced of the network, convolution neural networks. For grayscale images and high-dimensional image, s
hed-master
- We develop a new edge detection algorithm, holistically-nested edge detection (HED), which performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets. HED automat
gait-recognition-master
- I利用了深度学习，实现视频中的人的步态行为检测。(In this project you can find implementation of deep neural network for people identification from video by the characteristic of their gait. The processing is very robust against various covariate factors such as clothing, ca
Convolutional-neural-Network-master
- matlab，深度学习工具箱，经典的卷积神经网络，共有两层卷积层。输入为28*28*1的图片(Matlab, the deep learning toolbox, the classic convolution neural network, has two volumes of layers. A picture entered into 28*28*1)
tf-pose-estimation-master
- OpenPose人体姿态识别项目是美国卡耐基梅隆大学（CMU）基于卷积神经网络和监督学习并以caffe为框架开发的开源库。可以实现人体动作、面部表情、手指运动等姿态估计。适用于单人和多人，具有极好的鲁棒性。是世界上首个基于深度学习的实时多人二维姿态估计应用，基于它的实例如雨后春笋般涌现。人体姿态估计技术在体育健身、动作采集、3D试衣、舆情监测等领域具有广阔的应用前景，人们更加熟悉的应用就是抖音尬舞机(OpenPost Human Attitude Recognition Project is a