13 |
12 |
13 |
15 | Figure 1. Research Progress in Deep Learning. 16 |
17 | 18 |
19 | 
20 |
22 | Figure 2. Research Progress in Representation Learning for Networks. 23 |
24 | 25 | ## 书籍资料 26 | 27 | * 《深度学习》花书，由三位全球知名专家IanGoodfellow、YoshuaBengio、AaronCourville编著. 地址: [[深度学习AI圣经(Deep Learning)](https://github.com/MingchaoZhu/DeepLearning)] 28 | * 南京大学周志华老师的《机器学习》西瓜书/南瓜书. 地址: [[PumpkinBook)](https://github.com/datawhalechina/pumpkin-book)] 29 | 30 | ## 科研资源 31 | 32 | 需要连接学校网络，才可以免费下载论文资源： 33 | * IEEE-Xplore (所有信息化专业+交通-航天-汽车-机械等部分工科专业的科研论文). 地址: [[IEEE-Xplore)](https://ieeexplore.ieee.org/Xplore/home.jsp)] 34 | * ACM-library (计算机科学CS类的科研论文). 地址: [[ACM-library)](https://dl.acm.org/journals)] 35 | * Scopus (主要用于查询/检索某个科研作者出版的所有被SCI+EI检索的期刊+会议论文). 地址: [[Scopus)](https://www.scopus.com/search/form.uri?display=basic&zone=header&origin=searchbasic#basic)] 36 | 37 | 通用不限制学科的免费下载论文资源： 38 | * Google Scholar 地址: [[Google-Scholar)](https://scholar.google.com.hk/?hl=zh-CN)] 39 | * arXiv (预印版论文、不全) 地址: [[Arxiv)](https://arxiv.org/)] 40 | 41 | ## 深度学习框架 42 | * 菜鸟教程. 地址: [[Python3)](https://www.runoob.com/python3/python3-tutorial.html)] 43 | * PyTorch中文文档. 地址: [[PyTorch)](https://pytorch-cn.readthedocs.io/zh/latest/)] 44 | * PyTorch学习资源汇总. 地址: [[Awesome-PyTorch-Chinese)](https://github.com/INTERMT/Awesome-PyTorch-Chinese)] 45 | * PyTorch入门实战视频教程+配套源代码+PPT. 地址: [[PyTorch-Tutorials)](https://github.com/dragen1860/Deep-Learning-with-PyTorch-Tutorials)] 46 | * PyTorch官方中文教程包含60分钟快速入门教程. 地址: [[PyTorch-Docs)](https://github.com/fendouai/PyTorchDocs)] 47 | * PyTorch-计算机视觉CV学习. 地址: [[PyTorch-CV)](https://github.com/AccumulateMore/CV)] 48 | 49 | ## 有数据集的比赛网站 50 | 51 | ## 深度学习DL领域中里程碑式的15个模型 52 | | NO. | Year | Model | 1st-Author | Title | Publication | 53 | |:--:| :--: | :--: | :--: | :--: | :--: | 54 | | 1 | 1997 | LSTM | Sepp Hochreiter | Long Short-Term Memory | Neural Computation | 55 | | 2 | 1998 | CNN | Yann LeCun | Gradient-Based Learning Applied to Document Recognition | Proceedings of the IEEE | 56 | | 3 | 2012 | AlexNet | Alex Krizhevsky | ImageNet Classification with Deep Convolutional Neural Networks | NeurIPS | 57 | | 4 | 2014 | GRU | Kyunghyun Cho | Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation | EMNLP | 58 | | 5 | 2014 | GAN | Ian J. Goodfellow | Generative Adversarial Networks | NeurIPS | 59 | | 6 | 2015 | Attention | Dzmitry Bahdanau | Neural Machine Translation by Jointly Learning to Align and Translate | ICLR | 60 | | 7 | 2015 | VGGNet | Karen Simonyan | Very Deep Convolutional Networks for Large-Scale Image Recognition | ICLR | 61 | | 8 | 2015 | U-Net | Olaf Ronneberger | U-Net: Convolutional Networks for Biomedical Image Segmentation | MICCAI | 62 | | 9 | 2016 | ResNet | Kaiming He | Deep Residual Learning for Image Recognition | CVPR | 63 | | 10 | 2017 | Transformer | Ashish Vaswani | Attention Is All You Need | NeurIPS | 64 | | 11 | 2017 | GCN | Kipf, Thomas N | Semi-Supervised Classification with Graph Convolutional Networks | ICLR | 65 | | 12 | 2018 | GAT | P. Veliˇckovi´c | Graph Attention Networks | ICLR | 66 | | 13 | 2018 | GPT | Alec Radford | Improving Language Understanding by Generative Pre-training | OpenAI Blog | 67 | | 14 | 2019 | BERT | Jacob Devlin | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | NAACL-HLT | 68 | | 15 | 2020 | Diffusion | Jonathan Ho | Denoising Diffusion Probabilistic Models | NeurIPS | 69 | 70 |
71 | 
72 |
74 | Figure 3. Milestone Models in the Field of Deep Learning (DL). 75 |
76 | --------------------------------------------------------------------------------