This book consists of six chapters, which can be grouped into three subjects. The first subject is Machine Learning and takes place in Chapter 1. Deep Learning stems from Machine Learning. This implies that if you want to understand the essence of Deep Learning, you have to know the philosophy behind Machine Learning to some extent. Chapter 1 starts with the relationship between Machine Learning and Deep Learning, followed by problem solving strategies and fundamental limitations of Machine Learning. The detailed techniques are not introduced yet. Instead, fundamental concepts that applies to both the neural network and Deep Learning will be covered. The second subject is artificial neural network. Chapters 2-4 focuses on this subject. As Deep Learning is a type of Machine Learning that employs a neural network, the neural network is inseparable from Deep Learning. Chapter 2 starts with the fundamentals of the neural network: principles of its operation, architecture, and learning rules. It also provides the reason that the simple single-layer architecture evolved to the complex multi-layer architecture. Chapter 3 presents the backpropagation algorithm, which is an important and representative learning rule of the neural network and also employed in Deep Learning. This chapter explains how cost functions and learning rules are related and which cost functions are widely employed in Deep Learning. Chapter 4 introduces how to apply the neural network to classification problems. We have allocated a separate section for classification because it is currently the most prevailing application of Machine Learning. For example, image recognition, one of the primary applications of Deep Learning, is a classification problem. The third topic is Deep Learning. It is the main topic of this book as well. Deep Learning is covered in Chapters 5 and 6. Chapter 5 introduces the drivers that enables Deep Learning to yield excellent performance. For a better understanding, it starts wi
2021-11-18 15:48:21 1.74MB Deep Learning 深度学习 笔记
1
吴恩达在coursera上免费的斯坦福deep learning课程的同步资料,包含完整的matlab代码与PDF文档说明
2021-11-18 15:11:42 28.92MB deep learnin Andrew Ng
1
蛋白质网 ProteinNet是用于机器学习蛋白质结构的标准化数据集。 它提供蛋白质序列,结构(和),多个序列比对( ),位置特定的评分矩阵( ),以及标准化的拆分。 ProteinNet建立在两年期评估的基础上,该评估对最近解决但尚未公开获得的蛋白质结构进行盲目预测,以提供推动计算方法学前沿的测试集。 它被组织为一系列数据集,涵盖了CASP 7至12(涵盖十年),以提供一系列数据集大小,从而可以在相对数据贫乏和数据丰富的体制中评估新方法。 请注意,这是一个初步版本。 用于构建数据集的原始数据以及MSA尚未普遍可用。 但是,可应要求提供ProteinNet 12的原始MSA数据(4TB)
1
pybullet快速入门手册 PyBulletQuickstart GuideErwin Coumans​, ​Yunfei Bai​, 2017/2018 1.Introduction 2.controlling arobot 3.synthetic camera rendering 4.collision detection queries 5.inverse dynamics,kinematics 6.reinforcement learning gym envs 7.virtual reality 8.debug GUI,lines,Text,Parameters 9.build and install pybullet
2021-11-18 11:20:17 1.54MB deep rl pybullet robot
1
快速语义分割 该存储库旨在为PyTorch中的移动设备提供准确的实时语义分段代码,并在Cityscapes上提供预训练的权重。 这可用于在各种现实世界的街道图像上进行有效的分割,包括Mapillary Vistas,KITTI和CamVid等数据集。 from fastseg import MobileV3Large model = MobileV3Large . from_pretrained (). cuda (). eval () model . predict ( images ) 这些模型是MobileNetV3 (大型和小型变体)的实现,具有基于LR- ASPP的修改后的细分头。 顶级型号在Cityscapes val上能够达到72.3%的mIoU精度,而在GPU上以高达37.3 FPS的速度运行。 请参阅下面的详细基准。 当前,您可以执行以下操作: 加载预训练的Mo
1
2019-2021最新应用深度学习到OFDM通信系统中的论文汇总 赠人玫瑰,手有余香,可以顺便Star一下啦 2021 年 2021年面向深度学习的信号处理综述 2021-1月号发表 OFDM的无线图像传输的深层联合源信道编码 2021-1月, 提出的模型驱动的机器学习方法消除了对单独的源代码和信道编码的需求,同时集成了OFDM数据路径以应对多路径衰落信道 2021-1月,消除OFDM带来的麻烦:采用端到端学习的无导频和无CP通信 2021-1月,水下声OFDM通信中带软反馈的卷积神经网络降低PAPR 2021 International Bhurban Conference on Applied Sciences and Technologies (IBCAST) 2021-4月,使用信道状态信息进行OFDM系统中的物理篡改攻击检测:一种深度学习方法 IEEE Wireless Comm
2021-11-18 10:08:16 3KB
1
使用图像到图像的翻译进行无限制的面部几何重构-官方PyTorch实施 使用图像到图像转换的无限制面部几何重构的评估代码。终于移植到PyTorch! 最近更新 2020.10.27 :添加了STL支持 2020.05.07 :添加了车轮包装! 2020.05.06 :添加了版本以用于模型的快速测试 2020.04.30 :pyTorch初始版本 此版本中有什么内容? 由三部分组成 一个网络执行图像到深度+在合成人脸数据上训练的对应图 一种非刚性ICP方案,用于将输出图转换为完整的3D网格 从阴影到形状的方案,用于添加精细的介观细节 这个仓库目前包含我们的图像到图像网络,其中包含权重和PyTorch模型以及一个简单的python后处理方案。 已发布的网络经过了合成图像和未标记真实图像的组合训练,以增强鲁棒性:) 安装 从PyPi安装 $ pip install pix2vertex
2021-11-17 21:11:50 2.69MB deep-learning pytorch reconstruction iccv
1
人工神经网络漫谈.zip
2021-11-17 20:08:03 2.68MB deep learning
1
胶囊网络 胶囊网络的PyTorch实现,如Sara Sabour,Nicholas Frosst和Geoffrey E Hinton在论文中所述。
2021-11-17 19:51:57 5KB python deep-learning pytorch python-3
1
kaggle数据集 可供所有人使用的Kaggle数据集集合 系统 Python 3.5 Python 3.6 Python 3.7 Linux 苹果系统 视窗 有关Kaggle数据集的更多信息 import kaggledatasets as kd heart_disease = kd . structured . HeartDiseaseUCI ( download = True ) # Returns the pandas data frame to be used in Scikit Learn or any other framework df = heart_disease . data_frame () # Returns the tensorflow dataset type compatible with TF 2.0 dataset = heart_disease . load () for batch , label in dataset . take ( 1 ): for key , value in batch . items ():
1