|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/convolutional-neural-networks/
课程评论：没有评论
**课程名称： 深度学习：卷积神经网络 (Deep Learning: Convolutional Neural Networks)** **课程概述：** 本课程旨在为初学者到高级水平的学习者提供深度学习和卷积神经网络（CNN）的基础知识。无论您是计算机科学或工程专业的学生，还是热衷于人工智能领域的程序员，本课程都将帮助您理解卷积神经网络的核心原理，并达到专业水平。课程将重点探讨当前流行的深度学习算法和模型的理论基础。 **课程内容概要：** * **第一部分：卷积神经网络简介** * 深度学习入门 * ImageNet挑战 * 传统神经网络的局限性 * CNN的动机与历史 * **第二部分：卷积神经网络的特性** * 局部连接性 * 参数共享 * 池化与子采样 * **第三部分：卷积操作** * 卷积的定义 * 图像卷积示例 * 其他滤波器 * **第四部分：卷积神经网络的层** * 卷积层 * 带步幅的卷积 * 带步幅和填充的卷积 * 体积卷积 * 激活函数（ReLU） * 池化层 * 卷积网络 * BatchNormalization层 * **第五部分：卷积神经网络架构** * CNN架构简介 * LeNet-5 * AlexNet & ZFNet * VGGNet * GoogleNet (Inception Network) * Inception V2, V3, V4, Inception-ResNet-v1, Inception-ResNet-v2 * Xception * 残差神经网络 (ResNet) * DenseNet * **第六部分：用于目标检测的CNN** * 计算机视觉任务 * 目标定位与检测简介 * 分类+定位 * 基于滑动窗口的目标检测 * R-CNN * Fast R-CNN * Faster R-CNN * You only look once (YOLO) * **第七部分：用于实例分割的CNN** * 实例分割 * Mask R-CNN * **第八部分：用于语义分割的CNN** * 语义分割 * 基于滑动窗口的语义分割 * 全卷积网络 (Fully Convolutional Network) * 带转置卷积的上采样 * 全卷积网络：跳跃连接
كورس لتعليم اساسيات التعلم العميق والشبكات العصبية الالتفافية للمبتدئين وحتى المستوى المتقدمسواء كنت طالباً فى علوم الحاسب او طالباً فى الهندسة أو مبرمجاً وتعشق مجال الذكاء الاصطناعى , فإن هذا الكورس سيساعدك علي فهم أساسيات التعلم الشبكات العصبيه الالتفافية و الوصول إلى مستوى محترف وسوف يركز هذا الكورس على الجوانب النظرية وراء الخوارزميات والنماذج المنتشره هذه الايام للتعلم العميقThis course is focus on the theoretical aspects of the recent convolutional neural network based methods.######################################################################################################################################Section 1: Introduction to Convolutional Neural Network (CNN)Lecture 1: Introduction to Deep LearningLecture 2: ImageNet ChallengeLecture 3: Drawbacks of Previous Neural NetworksLecture 4: CNN Motivation & HistorySection 2: Convolutional Neural Network PropertiesLecture 5: Local ConnectivityLecture 6: Parameter SharingLecture 7: Pooling & SubsamplingSection 3: Convolution OperationLecture 8: Definition of ConvolutionLecture 9: Image Convolution ExampleLecture 10: Other FiltersSection 4: Convolutional Neural Network LayersLecture 11: Convolutional LayerLecture 12: Strided ConvolutionLecture 13: Strided Convolution with PaddingLecture 14: Convolution over VolumeLecture 15: Activation Function (ReLU)Lecture 16: Pooling LayerLecture 17: Convolutional NetworkLecture 18: BatchNormalization LayerSection 5: Convolutional Neural Network ArchitecturesLecture 19: Introduction to CNN ArchitecturesLecture 20: LeNet-5Lecture 21: AlexNet & ZFNetLecture 22: VGGNetLecture 23: GoogleNet (Inception Network)Lecture 24: Inception V2, V3, V4, Inception-ResNet-v1, Inception-ResNet-v2Lecture 25: XceptionLecture 26: Residual Neural Network (ResNet)Lecture 27: DenseNetSection 6: CNN for Object DetectionLecture 28: Computer Vision TasksLecture 29: Introduction to Object Localization and DetectionLecture 30: Classification + LocalizationLecture 31: Object Detection with Sliding WindowLecture 32: R-CNNLecture 33: Fast R-CNNLecture 34: Faster R-CNNLecture 35: You only look once (YOLO)Section 7: CNN for Instance SegmentationLecture 36: Instance SegmentationLecture 37: Mask R-CNNSection 8: CNN for Semantic SegmentationLecture 38: Semantic SegmentationLecture 39: Semantic Segmentation with Sliding WindowLecture 40: Fully Convolutional NetworkLecture 41: Up-sampling with Transposed ConvolutionLecture 42: Fully Convolutional Network: Skipping Connections
