下载频道  >  nwpuhtxy2010的资源
  • Deep Learning with Keras+标签完整无水印+文字可编辑复制

    Implement neural networks with Keras on Theano and TensorFlow The book presents more than 20 working deep neural networks coded in Python using Keras, a modular neural network library that runs on top of either Google's TensorFlow or Lisa Lab's Theano backends. The reader is introduced step by step to supervised learning algorithms such as simple linear regression, classical multilayer perceptron, and more sophisticated deep convolutional networks and generative adversarial networks. In addition, the book covers unsupervised learning algorithms such as autoencoders and generative networks. Recurrent networks and long short-term memory (LSTM) networks are also explained in detail. The book goes on to cover the Keras functional API and how to customize Keras in case the reader's use case is not covered by Keras's extensive functionality. It also looks at larger, more complex systems composed of the building blocks covered previously. The book concludes with an introduction to deep reinforcement learning and how it can be used to build game playing AIs. Practical applications include code for the classification of news articles into predefined categories, syntactic analysis of texts, sentiment analysis, synthetic generation of texts, and parts of speech annotation. Image processing is also explored, with recognition of handwritten digit images, classification of images into different categories, and advanced object recognition with related image annotations. An example of identification of salient points for face detection will be also provided. Sound analysis comprises recognition of discrete speeches from multiple speakers. Reinforcement learning is used to build a deep Q-learning network capable of playing games autonomously. Experiments are the essence of the book. Each net is augmented by multiple variants that progressively improve the learning performance by changing the input parameters, the shape of the network, loss functions, and algorithms used for optimizations. Several comparisons between training on CPUs and GPUs are also provided. 全书8章310页,主要聚焦于keras api的使用,推荐给炼丹的同学

    2019-05-23
    7
  • Deep Learning with Keras+高清无码无水印+文字可编辑复制+标签完整+质量上乘强烈推荐

    Implement neural networks with Keras on Theano and TensorFlow The book presents more than 20 working deep neural networks coded in Python using Keras, a modular neural network library that runs on top of either Google's TensorFlow or Lisa Lab's Theano backends. The reader is introduced step by step to supervised learning algorithms such as simple linear regression, classical multilayer perceptron, and more sophisticated deep convolutional networks and generative adversarial networks. In addition, the book covers unsupervised learning algorithms such as autoencoders and generative networks. Recurrent networks and long short-term memory (LSTM) networks are also explained in detail. The book goes on to cover the Keras functional API and how to customize Keras in case the reader's use case is not covered by Keras's extensive functionality. It also looks at larger, more complex systems composed of the building blocks covered previously. The book concludes with an introduction to deep reinforcement learning and how it can be used to build game playing AIs. Practical applications include code for the classification of news articles into predefined categories, syntactic analysis of texts, sentiment analysis, synthetic generation of texts, and parts of speech annotation. Image processing is also explored, with recognition of handwritten digit images, classification of images into different categories, and advanced object recognition with related image annotations. An example of identification of salient points for face detection will be also provided. Sound analysis comprises recognition of discrete speeches from multiple speakers. Reinforcement learning is used to build a deep Q-learning network capable of playing games autonomously. Experiments are the essence of the book. Each net is augmented by multiple variants that progressively improve the learning performance by changing the input parameters, the shape of the network, loss functions, and algorithms used for optimizations. Several comparisons between training on CPUs and GPUs are also provided. 全书8章310页,主要聚焦于keras api的使用,推荐给炼丹的同学

    2019-05-23
    9
  • Problem Solving with Python 3.6 Edition+高清无码无水印+目录附录完整+文字可编辑复制

    Overview: You will find the book chapters on the left hand menu You will find navigation within a section of a chapter (one webpage) on the righthand menu Full documentation on how to build this site locally are on GitHub at github.com/professorkazarinoff/Problem-Solving-with-Python/website Motivation: The motivation for writing this book is that many undergraduate engineering students have to take a programming course based on MATLAB. MATLAB is a great piece of software, but it currently costs $49.00 for a student license and requires a site license to be used on school computers. Subsequently, it is costly for a student to use MATLAB and it is costly for a college to support a course that uses MATLAB. In addition, this site license expires eventually and students need to purchase another copy often before they finish their degree. The Python programming language, on the other hand, is open source and free. To download and use Python, the cost to both the student and the college is zero (minus time spent). By moving an undergraduate engineering programming class to Python, students will save money and have greater access to the software they use in class. Further in their engineering education, students can continue to use Python for free. 全书共计13章,326页,专注于解决使用Python过程中常见的各种问题,既包括Python本身的问题,也包括常用的各种工具箱的使用问题,非常实用,强烈推荐!

    2019-05-23
    5
  • 《机器学习与应用》2019清华大学雷明编著最新版+全书21章588页+书签完整

    机器学习是当前解决很多人工智能问题的核心技术,深度学习的出现带来了自2012 年以来的人工智 能复兴。本书是机器学习和深度学习领域的人门与提高教材,系统、深入地讲述机器学习与深度学习的主 流方法与理论,并紧密结合工程实践与应用。全书由21 章组成,共分为三大部分。第1 ~ 3 章为第一部 分,介绍机器学习的基本原理、所帘的数学知识(包括微积分、线性代数、概率论和最优化方法), 以及机器 学习中的核心概念。第4 ~ 20 章为第二部分,是本书的主体,介绍各种常用的有监督学习算法、无监督学 习算法、半监督学习算法和强化学习算法。对于每种算法,从原理与推导、工程实现和实际应用3 个方面 进行介绍,对于大多数弈,法,都配有实验程序。第2 1 章为第三部分,介绍机苦苦学习和深度学习算法实际应 用时面11伍的问题,并给出典型的解决方案。此外,附录A 给出各种机器学习算法的总结, 附录B 给出梯度 下降法的演化关系,附录C 给出EM 算法的推导。 本书理论推导与证明详细、深入,结构清晰,详细地调述主要算法的工程实现细节,配以著名开源库的 源代码分析(包括lib svm 、liblin ear 、O pe n CV 、Ca ff e 等开源库),让读者不仅知其然,还知其所以然, 真正理解 算法、学会使用算法。对于计算- 机、人工智能及相关专业的本科生和研究生,这是一本适合人门与系统学 习的教材,对于从事人工智能和机器学习产品研发的工程技术人员,本书也具有很强的参考价值。

    2019-05-21
    13
  • Graph Algorithms:Practical Examples in Apache Spark and Neo4j+高清无码书签完整内容可编辑完美资源

    Graph Algorithms by Mark Needham and Amy E. Hodler Copyright © 2019 Amy Hodler and Mark Needham. All rights reserved. What’s in This Book This book is a practical guide to getting started with graph algorithms for developers and data scientists who have experience using Apache Spark™ or Neo4j. Although our algorithm examples utilize the Spark and Neo4j platforms, this book will also be helpful for understanding more general graph concepts, regardless of your choice of graph technologies. The first two chapters provide an introduction to graph analytics, algorithms, and theory. The third chapter briefly covers the platforms used in this book before we dive into three chapters focusing on classic graph algorithms: pathfinding, centrality, and community detection. We wrap up the book with two chapters showing how graph algorithms are used within workflows: one for general analysis and one for machine learning. At the beginning of each category of algorithms, there is a reference table to help you quickly jump to the relevant algorithm. For each algorithm, you’ll find: • An explanation of what the algorithm does • Use cases for the algorithm and references to where you can learn more • Example code providing concrete ways to use the algorithm in Spark, Neo4j, or both 图方法方面最新的参考书,本文理论实践兼备(看标题就知道了),内容高清无码书签完整诚不我欺,强烈推荐给需要的朋友!

    2019-05-21
    23
  • 深度学习框架PyTorch:入门与实践+完整标签+高清无码无水印

    深度学习框架PyTorch:入门与实践+完整标签+高清无码无水印,陈云编著。 从多维数组Tensor开始,循序渐进地带领读者了解PyTorch各方面的基础知识。结合基础知识和前沿研究,带领读者从零开始完成几个经典有趣的深度学习小项目,包括GAN生成动漫头像、AI滤镜、AI写诗等。《深度学习框架PyTorch:入门与实践》没有简单机械地介绍各个函数接口的使用,而是尝试分门别类、循序渐进地向读者介绍PyTorch的知识,希望读者对PyTorch有一个完整的认识。 《深度学习框架PyTorch:入门与实践》内容由浅入深,无论是深度学习的初学者,还是第一次接触PyTorch的研究人员,都能在学习本书的过程中快速掌握PyTorch。即使是有一定PyTorch使用经验的用户,也能够从本书中获得对PyTorch不一样的理解。 1 PyTorch简 介 1 1.1 PyTorch的诞生 1 1.2 常见的深度学习框架简介 2 1.2.1 Theano 3 1.2.2 TensorFlow 3 1.2.3 Keras 5 1.2.4 Caffe/Caffe2 5 1.2.5 MXNet 6 1.2.6 CNTK 7 1.2.7 其他框架 8 1.3 属于动态图的未来 8 1.4 为什么选择PyTorch 10 1.5 星火燎原 12 1.6 fast.ai 放弃Keras+TensorFlow选择PyTorch 13 2 快速入门 16 2.1 安装与配置 16 2.1.1 安装PyTorch 16 2.1.2 学习环境配置 20 2.2 PyTorch入门第一步 30 2.2.1 Tensor 30 2.2.2 Autograd:自动微分 35 2.2.3 神经网络 38 2.2.4 小试牛刀:CIFAR-10分类 43 3 Tensor和autograd 51 3.1 Tensor 51 3.1.1 基础操作 52 3.1.2 Tensor和Numpy 70 3.1.3 内部结构 73 3.1.4 其他有关Tensor的话题 76 3.1.5 小试牛刀:线性回归 78 3.2 autograd 81 3.2.1 Variable 82 3.2.2 计算图 86 3.2.3 扩展autograd 94 3.2.4 小试牛刀:用Variable实现线性回归 99 4 神经网络工具箱nn 103 4.1 nn.Module 103 4.2 常用的神经网络层 107 4.2.1 图像相关层 107 4.2.2 激活函数 110 4.2.3 循环神经网络层 114 4.2.4 损失函数 116 4.3 优化器 116 4.4 nn.functional 118 4.5 初始化策略 120 4.6 nn.Module深入分析 122 4.7 nn和autograd的关系 129 4.8 小试牛刀:用50行代码搭建ResNet 130 5 PyTorch中常用的工具 135 5.1 数据处理 135 5.2 计算机视觉工具包:torchvision 147 5.3 可视化工具 149 5.3.1 Tensorboard 150 5.3.2 visdom 152 5.4 使用GPU加速:cuda 158 5.5 持久化 161 6 PyTorch实战指南 164 6.1 编程实战:猫和狗二分类 164 6.1.1 比赛介绍 165 6.1.2 文件组织架构 165 6.1.3 关于__init__.py 167 6.1.4 数据加载 167 6.1.5 模型定义 170 6.1.6 工具函数 171 6.1.7 配置文件 174 6.1.8 main.py 176 6.1.9 使用 184 6.1.10 争议 185 6.2 PyTorch Debug 指南 187 6.2.1 ipdb 介绍 187 6.2.2 在PyTorch中Debug 191 7 AI插画师:生成对抗网络 197 7.1 GAN的原理简介 198 7.2 用GAN生成动漫头像 202 7.3 实验结果分析 211 8 AI艺术家:神经网络风格迁移 215 8.1 风格迁移原理介绍 216 8.2 用PyTorch实现风格迁移 222 8.3 实验结果分析 233 9 AI诗人:用RNN写诗 237 9.1 自然语言处理的基础知识 237 9.1.1 词向量 238 9.1.2 RNN 240 9.2 CharRNN 243 9.3 用PyTorch实现CharRNN 246 9.4 实验结果分析 257 10 Image Caption:让神经网络看图讲故事 260 10.1 图像描述介绍 261 10.2 数据 262 10.2.1 数据介绍 262 10.2.2 图像数据处理 270 10.2.3 数据加载 272 10.3 模型与训练 275 10.4 实验结果分析 280 11 展望与未来 282 11.1 PyTorch的局限与发展 282 11.2 使用建议 286

    2019-04-30
    8
  • Interpretable Machine Learning+ 高清无码+ 无水印 + 机器学习黑盒

    Christoph Molnar最新上线的电子书Interpretable Machine Learning+高清无码+无水印,主要是关于机器学习可解释性方面的论述,全书二百多页,很细致,对于理解深度学习黑盒很有帮助,推荐给喜欢的朋友!

    2019-04-23
    5
  • Interpretable Machine Learning+高清无码+无水印

    Christoph Molnar最新上线的电子书Interpretable Machine Learning+高清无码+无水印,主要是关于机器学习可解释性方面的论述,全书二百多页,很细致,对于理解深度学习黑盒很有帮助,推荐给喜欢的朋友!

    2019-04-23
    9
  • Information Theory and Network Coding Springer 2008+英文原版+高清无码无水印+书签完整

    Information Theory and Network Coding Springer 2008+英文原版+高清无码无水印+书签完整,本书已有蔡宁等翻译版,此书为英文原版,推荐给喜欢读原文的朋友!

    2019-04-03
    6
  • 奥本海默信号与系统答案(第二版)-中文版习题解答

    奥本海默信号与系统答案(第二版)-中文版习题解答,全文高清700多页,内容详细面面俱到,包括全部的课后习题,目录完整,无广告等等乱七八糟的东西,强烈推荐给大家学习!

    2019-03-07
    29
img

关注 私信


用户积分:2522