《ImageNet Classification with Deep Convolutional Neural Networks》
首先申明本人的英语很搓，看英文非常吃力，只能用这种笨办法来方便下次阅读。有理解错误的地方，请别喷我。CNN怎么应用到NLP什么是卷积和什么是卷积神经网络就不讲了，自行google。从在自然语言处理的应用开始(SO, HOW D
Convolutional Neural Networks are very similar to ordinary Neural Networks from the previous chapter: they are made up of neurons that have learnable weights and biases. Each neuron receives some inputs, performs a dot product and optionally follows it with a non-linearity.
The state-of-the-art methods used for relation <em>classification</em> are primarily based on statistical machine learning, and their performance strongly depends on the quality of the extracted features. The extracted features are often derived from the output of pre-existing natural language processing (NLP) systems, which leads to the propagation of the errors in the existing tools and hinders the performance of these systems.
"Discrimination-aware Channel Pruning for Deep Neural Networks"这篇文章首先认为通道剪枝能够确保剪枝后模型与现有深度学习框架兼容，避免非规整的稀疏运算。其次基于训练的通道剪枝策略，需要在训练过程中施加稀疏约束或正则化约束，通常消耗较大的训练时间。另外基于最小化输出特征重建误差、layer-by-layer方式的剪枝策略（channel ...
Deep Learning and Convolutional Neural Networks for Medical Image Computing: Precision Medicine, High Performance and Large-Scale Datasets (Advances in Computer Vision and Pattern Recognition) by Le Lu, Yefeng Zheng, Gustavo Carneiro, Lin Yang
2017 | ISBN: 3319429981 | English | 326 pages | PDF | 14 MB
This book presents a detailed review of the state of the art in <em>deep</em> learning approaches for semantic object detection and segmentation in medical image computing, and large-scale radiology database mining. A particular focus is placed on the application of <em>convolutional</em> <em>neural</em> <em>networks</em>, with the theory supported by practical examples. Features: highlights how the use of <em>deep</em> <em>neural</em> <em>networks</em> can address new questions and protocols, as well as improve upon existing challenges in medical image computing; discusses the insightful research experience of Dr. Ronald M. Summers; presents a comprehensive review of the latest research and literature; describes a range of different methods that make use of <em>deep</em> learning for object or landmark detection tasks in 2D and 3D medical imaging; examines a varied selection of techniques for semantic segmentation using <em>deep</em> learning principles in medical imaging; introduces a novel approach to interleaved text and image <em>deep</em> mining on a large-scale radiology image database.
目前卷积神经网络的研究主要在两个方面：1 network structures 神经网络结构的这方面的论文有A. Coates, A. Y. Ng, and H. Lee. An analysis of single-layer <em>networks</em> in unsupervised feature learning. Journal ofMachine Learning Research, 2011....
DenseNet综述介绍_An Introduction Of Densely Connected Convolutional Networks.ppt 引用的参考文献，包含DeepLearning学习重要的几种网络的发表paper。
Deep Residual Learning for Image Recognition [ResNet]
Densely Connected Convolutional Networks [DenseNet]
Going <em>deep</em>er with convolutions [GoogleNet]
Gradient-Based Learning Applied to Document Recognition [LeNet-5]
ImageNet Classification with Deep Convolutional Neural Networks [ALexNet]
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION [VGGNet]
Both <em>convolutional</em> and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for...
Convolutional Neural Network
Convolutional Neural Networks (CNNs / ConvNets)Convolutional Neural Networks are very similar to ordinary Neural
在各种顶会论文中，对年龄和性别的检测的论文还是比较少的。而本文将要讲解的是2015年的一篇cvpr，Age and Gender Classification using Convolutional Neural Netw...
Exploring an advanced state of the art <em>deep</em> learning models and its applications using Popular python libraries like Keras, Tensorflow, and Pytorch
• A strong foundation on <em>neural</em> <em>networks</em> and <em>deep</em> learning with Python libraries.
• Explore advanced <em>deep</em> learning techniques and their applications across computer vision and NLP.
• Learn how a computer can navigate in complex environments with reinforcement learning.
With the surge of Artificial Intelligence in each and every application catering to both business and consumer needs, Deep Learning becomes the prime need of today and future market demands. This book explores <em>deep</em> learning and builds a strong <em>deep</em> learning mindset in order to put them into use in their smart artificial intelligence projects.
This second edition builds strong grounds of <em>deep</em> learning, <em>deep</em> <em>neural</em> <em>networks</em> and how to train them with high-performance algorithms and popular python frameworks. You will uncover different <em>neural</em> <em>networks</em> architectures like <em>convolutional</em> <em>networks</em>, recurrent <em>networks</em>, long short term memory (LSTM) and solve problems across image recognition, natural language processing, and time-series prediction. You will also explore the newly evolved area of reinforcement learning and it will help you to understand the state-of-the-art algorithms which are the main engines behind popular game Go, Atari, and Dota.
By the end of the book, you will be well versed with practical <em>deep</em> learning knowledge and its real-world applications
What you will learn
• Grasp mathematical theory behind <em>neural</em> <em>networks</em> and <em>deep</em> learning process.
• Investigate and resolve computer vision challenges using <em>convolutional</em> <em>networks</em> and capsule <em>networks</em>.
• Solve Generative tasks using Variational Autoencoders and Generative Adversarial Nets (GANs).
• Explore Reinforcement Learning and understand how agents behave in a complex environment.
• Implement complex natural language processing tasks using recurrent <em>networks</em> (LSTM, GRU), and attention models.
Who This Book Is For
This book is for Data Science practitioners, Machine Learning Engineers and Deep learning aspirants who have a basic foundation of Machine Learning concepts and some programming experience with Python. A mathematical background with a conceptual understanding of calculus and statistics is also desired
Convolutional <em>neural</em> <em>networks</em> (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. In this work, we introduce two new modul...
主要是对这几年ISCA ASPLOS DAC DATE ICCAD ASP-DAC等会议上有关AI硬件的文章进行整理：
- Efficient processing of <em>deep</em> <em>neural</em> <em>networks</em>: A tutorial and survey. Proceedings of the IEEE. (2017) Massa...
Variants of RNN
Jordan Network store output into memory
Long Short-term Memory LSTM
Relationship with original networkIntroduction假设我们想做一个
这里介绍2017ICLR OpenReview中的一篇有关网络加速的文章《DeepRebirth: A General Approach for Accelerating Deep Neural Network Execution on Mobile Devices》。 看文章标题觉得高大上，看方法细节觉得卧槽好水，看自己的验证结果好像还有点用。附：2017ICLR openreview http:
这是关于模型剪枝（Network Pruning）的一篇论文，论文题目是：Learning both weights and connections for efficient <em>neural</em> <em>networks</em>，作者在论文中提出了一种通过网络剪枝对模型进行压缩的思路，详细地描述了模型剪枝的思路，流程和方法。
论文地址：Learning both weights and connecti...
Convolutional Neural Networks (CNN) are one of the most popular architectures used in computer vision apps. This book is an introduction to CNNs through solving real-world problems in <em>deep</em> learning while teaching you their implementation in popular Python library - TensorFlow. By the end of the book, you will be training CNNs in no time!
一、 多任务课程学习Curriculum Learning of Multiple Tasks 1
二、 词典对分类器驱动卷积神经网络进行对象检测Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection 5
三、 用于同时检测和分割的多尺度贴片聚合（MPA）* Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation ∗ 7
四、 通过多任务网络级联实现感知语义分割Instance-aware Semantic Segmentation via Multi-task Network Cascades 10
五、 十字绣网络多任务学习Cross-stitch Networks for Multi-task Learning 15
六、 多任务相关粒子滤波器用于鲁棒物体跟踪Multi-Task Correlation Particle Filter for Robust Object Tracking 23
七、 多任务网络中的全自适应特征共享与人物属性分类中的应用Fully-Adaptive Feature Sharing in Multi-Task Networks With Applications in Person Attribute Classification 28
八、 超越triplet loss：一个深层次的四重网络，用于人员重新识别Beyond triplet loss: a <em>deep</em> quadruplet network for person re-identification 33
九、 弱监督级联卷积网络Weakly Supervised Cascaded Convolutional Networks 38
十、 从单一图像深度联合雨水检测和去除Deep Joint Rain Detection and Removal from a Single Image 43
十一、 什么可以帮助行人检测？What Can Help Pedestrian Detection? （将额外的特征聚合到基于CNN的行人检测框架） 46
十二、 人员搜索的联合检测和识别特征学习Joint Detection and Identification Feature Learning for Person Search 50
十三、 UberNet：使用多种数据集和有限内存训练用于低，中，高级视觉的通用卷积神经网络UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory 62
This book covers both classical and modern models in <em>deep</em> learning. The primary focus is on the theory and algorithms of <em>deep</em> learning. The theory and algorithms of <em>neural</em> <em>networks</em> are particularly important for understanding important concepts, so that one can understand the important design concepts of <em>neural</em> architectures in different applications. Why do <em>neural</em> <em>networks</em> work? When do they work better than off-the-shelf machine-learning models? When is depth useful? Why is training <em>neural</em> <em>networks</em> so hard? What are the pitfalls? The book is also rich in discussing different applications in order to give the practitioner a flavor of how <em>neural</em> architectures are designed for different types of problems. Applications associated with many different areas like recommender systems, machine translation, image captioning, image <em>classification</em>, reinforcement-learning based gaming, and text analytics are covered. The chapters of this book span three categories:
The basics of <em>neural</em> <em>networks</em>: Many traditional machine learning models can be understood as special cases of <em>neural</em> <em>networks</em>. An emphasis is placed in the first two chapters on understanding the relationship between traditional machine learning and <em>neural</em> <em>networks</em>. Support vector machines, linear/logistic regression, singular value decomposition, matrix factorization, and recommender systems are shown to be special cases of <em>neural</em> <em>networks</em>. These methods are studied together with recent feature engineering methods like word2vec.
Fundamentals of <em>neural</em> <em>networks</em>: A detailed discussion of training and regularization is provided in Chapters 3 and 4. Chapters 5 and 6 present radial-basis function (RBF) <em>networks</em> and restricted Boltzmann machines.
Advanced topics in <em>neural</em> <em>networks</em>: Chapters 7 and 8 discuss recurrent <em>neural</em> <em>networks</em> and <em>convolutional</em> <em>neural</em> <em>networks</em>. Several advanced topics like <em>deep</em> reinforcement learning, <em>neural</em> Turing machines, Kohonen self-organizing maps, and generative adversarial <em>networks</em> are introduced in Chapters 9 and 10.
The book is written for graduate students, researchers, and practitioners. Numerous exercises are available along with a solution manual to aid in classroom teaching. Where possible, an application-centric view is highlighted in order to provide an understanding of the practical uses of each class of techniques.