论文汇总
将自己学习的论文进行汇总和分析,从而更清楚地把握整体论文脉络(持更)
经典必读
原博客链接: link.
- ImageNet Classification with Deep Convolutional Networks(AlexNet)–起源 link.
- Visualizing and Understanding Convolutional Neural Networks(ZF Net) link.
- Adaptive deconvolutional networks for mid and high level feature learning(DeConvNet) link.
- Very Deep Convolutional Networks for large-Scale Image Recognition (VGG-Net) link
- Going Deeper with Convolutions (GoogLeNet) link
- Deep Residual Learning for Image Recognition (ResNet)
- Region Based CNNs (R-CNN,Fast R-CNN,Faster R-CNN)
- Generative Adversarial Networks (GAN)
- Genertating Image Descriptions
最新进展
- You Only Look Once (YOLO,YOLOv2,YOLOv3)
- Attention is All You Need
工程相关
1、损失函数(cross-entry)、分类函数(softmax)以及激活函数(relu)的选择
2、超完备稀疏表示简单理解(over-complete sparse representation)link
3、1×1卷积核
4、牛顿法与拟牛顿法–非线性优化算法 link
5、范数norm的简介