常见神经网络出处及下载链接 总览 整理下这些年主要的神经网络文献,包括了三大特征提取器(CNN/RNN/Transformer)、GAN等一些混合模型。不定期补充更新 总览 序号网络结构文献出处年份1RNN(序列模型起源)Learning representations by back-propagating errors19862CNN(卷积网络起源)Generalization and Network Design Strategies19893LSTMLong short-term memory19974BiLSTMFramewise phoneme classification with bidirectional LSTM and other neural network architectures20055AlexNetImageNet Classification with Deep Convolutional Neural Networks20126VGGNetVERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION20147GRULearning Phrase Representations Using RNN Encoder–Decoder for Statistical Machine Translation20148GANGenerative Adversarial Networks20149CGANConditional Generative Adversarial Nets201410CLDNNConvolutional, Long Short-Term Memory, fully connected Deep Neural Networks201511InceptionRethinking the Inception Architecture for Computer Vision201612ResNetDeep Residual Learning for Image Recognition201613GCN(图卷积)Semi-supervised Classification with Graph Convolutional Networks201614InfoGANInfogan: Interpretable representation learning by information maximizing generative adversarial nets201615YOLO v1版You Only Look Once: Unified, Real-Time Object Detection201616DenseNetDensely Connected Convolutional Networks201717Transformer(起源)Attention is all you need201718Mask R-CNNMask R-CNN201719Vision Transformer (ViT)An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale202020Pooling-based Vision Transformer (PiT)Rethinking spatial dimensions of vision transformers2021