# 精选高引用深度学习论文 **Repository Path**: alohaley/Most-Cited-Deep-Learning-Papers ## Basic Information - **Project Name**: 精选高引用深度学习论文 - **Description**: 高引用精选深度学习论文合集（中英对照翻译版） - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 4 - **Forks**: 1 - **Created**: 2024-12-19 - **Last Updated**: 2025-05-18 ## Categories & Tags **Categories**: Uncategorized **Tags**: 深度学习, Deep-learning, AI, 论文 ## README # Most-Cited-Deep-Learning-Papers 高引用精选Deep Learning论文（中英对照翻译） ## Understanding / Generalization / Transfer 理解 / 泛化 / 迁移 **Distilling the knowledge in a neural network (2015)** 神经网络中知识的提炼 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DTDD8iYQ7f6SDBipuPAFIAA)**
**Deep neural networks are easily fooled: High confidence predictions for unrecognizable images (2015)** 深度神经网络很容易被愚弄：为何对不可识别图像有高置信度预测 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dcyz7ScQ7f6SDBivuPAFIAA)**
**How transferable are features in deep neural networks? (2014)** 深度神经网络中的特征具有多大的可迁移性？(2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DVi6zL4Q7f6SDBixuPAFIAA)**
**CNN features off-the-Shelf: An astounding baseline for recognition (2014), A. Razavian et al.** 现成的CNN特征：识别任务的惊人基线 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Df43UJ0Q7f6SDBiyuPAFIAA)**
**Learning and transferring mid-Level image representations using convolutional neural networks (2014)** 如何使用卷积神经网络学习和迁移中层图像表示 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dal7jG4Q7f6SDBizuPAFIAA)**
**Visualizing and understanding convolutional networks (2014)** 如何可视化和理解卷积网络 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DRYMxfAQ7f6SDBi0uPAFIAA)**
**Decaf: A deep convolutional activation feature for generic visual recognition (2014)** Decaf：用于通用视觉识别的深度卷积激活特征 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DWaTMpMQ7f6SDBi1uPAFIAA)**
## Optimization / Training Techniques 优化 / 训练技术 **Training very deep networks (2015)** 训练深层网络
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DS88wPYQ7f6SDBjoxfAFIAA)**
**Batch normalization: Accelerating deep network training by reducing internal covariate shift (2015)** 批量归一化：通过减少内部协变量偏移加速深度网络训练
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DWFt5CgQ7f6SDBjzxfAFIAA)**
**Delving deep into rectifiers: Surpassing human-level performance on imagenet classification (2015)** 深入研究修正线性单元：在ImageNet分类上超越人类水平
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dby_aZUQ7f6SDBj0xfAFIAA)**
**Dropout: A simple way to prevent neural networks from overfitting (2014)** Dropout：防止神经网络过拟合的简单方法
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DUpw94IQ7f6SDBj3xfAFIAA)**
**Adam: A method for stochastic optimization (2014)** Adam：一种随机优化方法
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Df-mI4gQ7f6SDBj4xfAFIAA)**
**Improving neural networks by preventing co-adaptation of feature detectors (2012)** 通过防止特征检测器的共适应性来改进神经网络
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DfN4OlIQ7f6SDBj6xfAFIAA)**
**Random search for hyper-parameter optimization (2012)** 超参数优化的随机搜索
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DTGnLqkQ7f6SDBj7xfAFIAA)**
## Unsupervised / Generative Models 无监督/生成模型 **Pixel recurrent neural networks (2016)**
像素递归神经网络 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DT8wh1EQ7f6SDBjT8PAFIAA)**
**Improved techniques for training GANs (2016)**
改进的生成对抗网络训练技术 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DeMaTzYQ7f6SDBja8PAFIAA)**
**Unsupervised representation learning with deep convolutional generative adversarial networks (2015)**
使用深度卷积生成对抗网络的无监督表示学习 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DYbUqu0Q7f6SDBjj8PAFIAA)**
**DRAW: A recurrent neural network for image generation (2015)**
DRAW: 用于图像生成的递归神经网络 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DRTNP2UQ7f6SDBjl8PAFIAA)**
**Generative adversarial nets (2014)**
生成对抗网络 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DXiJ4rQQ7f6SDBjm8PAFIAA)**
**Auto-encoding variational Bayes (2013)**
自编码变分贝叶斯 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DTmbxZgQ7f6SDBjn8PAFIAA)**
**Building high-level features using large scale unsupervised learning (2013)**
使用大规模无监督学习构建高层特征 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dd03bY8Q7f6SDBjo8PAFIAA)**
## Convolutional Neural Network Models 卷积神经网络模型 **Rethinking the inception architecture for computer vision (2016)**
重新思考计算机视觉中的Inception架构 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/De2hm08Q7f6SDBik9vAFIAA)**
**Inception-v4, inception-resnet and the impact of residual connections on learning (2016)**
Inception-v4、Inception-ResNet及残差连接对学习的影响 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DSBihE4Q7f6SDBil9vAFIAA)**
**Identity Mappings in Deep Residual Networks (2016)**
深度残差网络中的恒等映射 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DWlF_fUQ7f6SDBim9vAFIAA)**
**Deep residual learning for image recognition (2016)**
用于图像识别的深度残差学习 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DS8t2XkQ7f6SDBin9vAFIAA)**
**Spatial transformer network (2015)**
空间变换网络 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DaCXSigQ7f6SDBio9vAFIAA)**
**Going deeper with convolutions (2015)**
通过卷积实现更深的网络 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DcgLiTQQ7f6SDBip9vAFIAA)**
**Very deep convolutional networks for large-scale image recognition (2014)**
用于大规模图像识别的超深卷积网络 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DfAE7dsQ7f6SDBir9vAFIAA)**
**Return of the devil in the details: delving deep into convolutional nets (2014)**
细节中的魔鬼回归：深入研究卷积网络 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DdwZBe8Q7f6SDBis9vAFIAA)**
**OverFeat: Integrated recognition, localization and detection using convolutional networks (2013)**
OverFeat: 使用卷积网络的集成识别、定位和检测 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DWhMK6sQ7f6SDBiu9vAFIAA)**
**Maxout networks (2013)**
Maxout网络 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DR9QHBIQ7f6SDBiv9vAFIAA)**
**Network in network (2013)**
网络中的网络 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DSksuJMQ7f6SDBix9vAFIAA)**
**ImageNet classification with deep convolutional neural networks (2012)**
使用深度卷积神经网络进行ImageNet分类 (2012)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dd7zNMAQ7f6SDBiz9vAFIAA)**
## Image: Segmentation / Object Detection 图像：分割/目标检测 **You only look once: Unified, real-time object detection (2016)**
你只看一次：统一的实时目标检测 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DQh2yJUQ7f6SDBiNw_EFIAA)**
**Fully convolutional networks for semantic segmentation (2015)**
用于语义分割的全卷积网络 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DUeCWlwQ7f6SDBiOw_EFIAA)**
**Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2015)**
Faster R-CNN：使用区域建议网络实现实时目标检测 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DYqDGRMQ7f6SDBiPw_EFIAA)**
**Fast R-CNN (2015)**
快速R-CNN (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dcnnb6YQ7f6SDBiWw_EFIAA)**
**Rich feature hierarchies for accurate object detection and semantic segmentation (2014)**
用于精确目标检测和语义分割的丰富特征层次结构 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DfT1aZMQ7f6SDBiYw_EFIAA)**
**Spatial pyramid pooling in deep convolutional networks for visual recognition (2014)**
用于视觉识别的深度卷积网络中的空间金字塔池化 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DSIiT-wQ7f6SDBicw_EFIAA)**
**Semantic image segmentation with deep convolutional nets and fully connected CRFs**
使用深度卷积网络和全连接条件随机场的语义图像分割
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DdgBILgQ7f6SDBigw_EFIAA)**
**Learning hierarchical features for scene labeling (2013)**
学习用于场景标注的层次特征 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DXO5CwYQ7f6SDBihw_EFIAA)**
## Image / Video / Etc 图像 / 视频 / 等等 **Image Super-Resolution Using Deep Convolutional Networks (2016)**
图像超分辨率使用深度卷积网络 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DYZEeaYQ7f6SDBjw1fEFIAA)**
**A Neural Algorithm of Artistic Style (2015)**
艺术风格的神经算法 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DUUD7LAQ7f6SDBjz1fEFIAA)**
**Deep Visual-Semantic Alignments for Generating Image Descriptions (2015)**
用于生成图像描述的深度视觉-语义对齐 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DbNeejYQ7f6SDBj01fEFIAA)**
**Show, Attend and Tell: Neural Image Caption Generation with Visual Attention (2015)**
展示、关注和讲述：带有视觉注意力的神经图像字幕生成 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DQhK8BUQ7f6SDBj71fEFIAA)**
**Show and Tell: A Neural Image Caption Generator (2015)**
展示和讲述：一个神经图像字幕生成器 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DVJHVggQ7f6SDBj41fEFIAA)**
**Long-term Recurrent Convolutional Networks for Visual Recognition and Description (2015)**
用于视觉识别和描述的长期递归卷积网络 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Db4Ca-MQ7f6SDBj91fEFIAA)**
**VQA: Visual Question Answering (2015)**
VQA：视觉问答 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dfh8KmMQ7f6SDBj81fEFIAA)**
**DeepFace: Closing the Gap to Human-Level Performance in Face Verification (2014)**
DeepFace：缩小人脸验证中与人类水平表现的差距 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DR73YUEQ7f6SDBj-1fEFIAA)**
**Large-Scale Video Classification with Convolutional Neural Networks (2014)**
使用卷积神经网络的大规模视频分类 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DXBRqAQQ7f6SDBj_1fEFIAA)**
**Two-Stream Convolutional Networks for Action Recognition in Videos (2014)**
视频中动作识别的双流卷积网络 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DcxwRtMQ7f6SDBiC1vEFIAA)**
**3D Convolutional Neural Networks for Human Action Recognition (2013)**
用于人体动作识别的3D卷积神经网络 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DWXBvDoQ7f6SDBiD1vEFIAA)**
## Natural Language Processing / RNNs 自然语言处理 / 循环神经网络 **Neural Architectures for Named Entity Recognition (2016)**
用于命名实体识别的神经架构 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dd_I1QEQ7f6SDBj61vEFIAA)**
**Exploring the Limits of Language Modeling (2016)**
探索语言建模的极限 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DeRf_BkQ7f6SDBj71vEFIAA)**
**Teaching Machines to Read and Comprehend (2015)**
教机器阅读和理解 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DZaTtWYQ7f6SDBj81vEFIAA)**
**Effective Approaches to Attention-Based Neural Machine Translation (2015)**
基于注意力的神经机器翻译的有效方法 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DU4IxZoQ7f6SDBj91vEFIAA)**
**Conditional Random Fields as Recurrent Neural Networks (2015)**
条件随机场作为递归神经网络 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DXKwMBgQ7f6SDBiA1_EFIAA)**
**Memory Networks (2014)**
记忆网络 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DYKt-g0Q7f6SDBiE1_EFIAA)**
**Neural Turing Machines (2014)**
神经图灵机 (2014)
**[中英对照翻译pdf]()**
**Neural Machine Translation by Jointly Learning to Align and Translate (2014)**
通过联合学习对齐和翻译的神经机器翻译 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DbasZqgQ7f6SDBiH1_EFIAA)**
**Sequence to Sequence Learning with Neural Networks (2014)**
使用神经网络的序列到序列学习 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DdfDQmcQ7f6SDBiJ1_EFIAA)**
**Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation (2014)**
使用RNN编码器-解码器学习短语表示用于统计机器翻译 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dc4LYjgQ7f6SDBiK1_EFIAA)**
**A Convolutional Neural Network for Modeling Sentences (2014)**
用于建模句子的卷积神经网络 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DV5U7zgQ7f6SDBiL1_EFIAA)**
**Convolutional Neural Networks for Sentence Classification (2014)**
用于句子分类的卷积神经网络 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DXgyjp4Q7f6SDBiM1_EFIAA)**
**Glove: Global Vectors for Word Representation (2014)**
Glove：词表示的全局向量 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DWFyxgUQ7f6SDBiN1_EFIAA)**
**Distributed Representations of Sentences and Documents (2014)**
句子和文档的分布式表示 (2014)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DcSM8iUQ7f6SDBiS1_EFIAA)**
**Distributed Representations of Words and Phrases and Their Compositionality (2013)**
单词和短语的分布式表示及其组合性 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DV_vOKcQ7f6SDBiT1_EFIAA)**
**Efficient Estimation of Word Representations in Vector Space (2013)**
在向量空间中高效估计词表示 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DVUx8hQQ7f6SDBiV1_EFIAA)**
**Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013)**
用于情感树库语义组合的递归深度模型 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dee4j5YQ7f6SDBic1_EFIAA)**
**Generating Sequences with Recurrent Neural Networks (2013)**
使用递归神经网络生成序列 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DZj-ymYQ7f6SDBid1_EFIAA)**
## Speech / Other Domain 语音 / 其他领域 **End-to-End Attention-Based Large Vocabulary Speech Recognition (2016)**
基于注意力的端到端大词汇量语音识别 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DSK1GN8Q7f6SDBiHmPIFIAA)**
**Deep Speech 2: End-to-End Speech Recognition in English and Mandarin (2015)**
Deep Speech 2：英语和普通话的端到端语音识别 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DS2VmuQQ7f6SDBiImPIFIAA)**
**Speech Recognition with Deep Recurrent Neural Networks (2013)**
使用深度递归神经网络的语音识别 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DYR4APQQ7f6SDBiJmPIFIAA)**
**Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups (2012)**
用于语音识别中声学建模的深度神经网络：四个研究小组的共同观点 (2012)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DSnsX7IQ7f6SDBiLmPIFIAA)**
**Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition (2012)**
用于大词汇量语音识别的上下文相关预训练深度神经网络 (2012)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DX6bQRYQ7f6SDBiMmPIFIAA)**
**Acoustic Modeling Using Deep Belief Networks (2012)**
使用深度信念网络进行声学建模 (2012)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DZFFD8cQ7f6SDBiNmPIFIAA)**
## Reinforcement Learning / Robotics 强化学习 / 机器人学 **End-to-end training of deep visuomotor policies (2016)** 深度视觉运动策略的端到端训练 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dbm9RBkQ7f6SDBjz3vIFIAA)**
**Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection (2016)** 使用深度学习和大规模数据收集学习机器人抓取的手眼协调 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DV8m3j8Q7f6SDBj03vIFIAA)**
**Asynchronous methods for deep reinforcement learning (2016)** 深度强化学习的异步方法 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DRYYULMQ7f6SDBj13vIFIAA)**
**Deep Reinforcement Learning with Double Q-Learning (2016)** 使用双Q学习的深度强化学习 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DZWxw58Q7f6SDBj23vIFIAA)**
**Mastering the game of Go with deep neural networks and tree search (2016)** 使用深度神经网络和树搜索掌握围棋游戏 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DT3tUxsQ7f6SDBj33vIFIAA)**
**Continuous control with deep reinforcement learning (2015)** 使用深度强化学习进行连续控制 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DS_lS8QQ7f6SDBj43vIFIAA)**
**Human-level control through deep reinforcement learning (2015)** 通过深度强化学习实现人类水平的控制 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DT3nsioQ7f6SDBiC3_IFIAA)**
**Deep learning for detecting robotic grasps (2015)** 用于检测机器人抓取的深度学习 (2015)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DYJa6vQQ7f6SDBiD3_IFIAA)**
**Playing atari with deep reinforcement learning (2013)** 使用深度强化学习玩Atari游戏 (2013)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DaJPCdoQ7f6SDBiE3_IFIAA)**
## More Papers from 2016 更多 2016 年的论文 **Layer Normalization (2016)** 层归一化 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DXGOjZIQ7f6SDBiclPMFIAA)**
**Learning to learn by gradient descent by gradient descent (2016)** 通过梯度下降学习学习 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DWvKgo8Q7f6SDBielPMFIAA)**
**Domain-adversarial training of neural networks (2016)** 神经网络的领域对抗训练 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DZfFknMQ7f6SDBiflPMFIAA)**
**WaveNet: A Generative Model for Raw Audio (2016)** WaveNet：一种原始音频的生成模型 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/De3-pD8Q7f6SDBiglPMFIAA)**
**Colorful image colorization (2016)** 彩色图像上色 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Dd0Zow8Q7f6SDBihlPMFIAA)**
**Generative visual manipulation on the natural image manifold (2016)** 在自然图像流形上的生成视觉操控 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DapfOMwQ7f6SDBijlPMFIAA)**
**Texture networks: Feed-forward synthesis of textures and stylized images (2016)** 纹理网络：纹理和风格化图像的前馈合成 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DZwN27AQ7f6SDBillPMFIAA)**
**SSD: Single shot multibox detector (2016)** SSD：单次多框检测器 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/Da3CnkEQ7f6SDBimlPMFIAA)**
**SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 1MB model size (2016)** SqueezeNet：以50倍更少的参数和小于1MB的模型大小达到AlexNet水平的准确性 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DQhv8o8Q7f6SDBiolPMFIAA)**
**Eie: Efficient inference engine on compressed deep neural network (2016)** Eie：压缩深度神经网络上的高效推理引擎 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DYby15kQ7f6SDBiplPMFIAA)**
**Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1 (2016)** 二值化神经网络：训练权重和激活值限制为+1或-1的深度神经网络 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DU89KggQ7f6SDBiqlPMFIAA)**
**Dynamic memory networks for visual and textual question answering (2016)** 用于视觉和文本问答的动态记忆网络 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DYDdUuUQ7f6SDBirlPMFIAA)**
**Stacked attention networks for image question answering (2016)** 用于图像问答的堆叠注意力网络 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DckoEMAQ7f6SDBislPMFIAA)**
**Hybrid computing using a neural network with dynamic external memory (2016)** 使用具有动态外部存储器的神经网络的混合计算 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DSAOfFwQ7f6SDBiulPMFIAA)**
**Google's neural machine translation system: Bridging the gap between human and machine translation (2016)** 谷歌的神经机器翻译系统：弥合人类和机器翻译之间的差距 (2016)
**[中英对照翻译pdf](https://www.jianguoyun.com/p/DQHDOHEQ7f6SDBiwlPMFIAA)**