Deep Learning: Convolutional Neural Networks

Convolutional Neural Networks (CNN) in Arabic التعلم العميق والشبكات الالتفافية باللغة العربية

Ratings: 4.76 / 5.00




Description

كورس لتعليم اساسيات التعلم العميق والشبكات العصبية الالتفافية للمبتدئين وحتى المستوى المتقدم

سواء 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 العميق

This 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 Learning

Lecture 2: ImageNet Challenge

Lecture 3: Drawbacks of Previous Neural Networks

Lecture 4: CNN Motivation & History


Section 2: Convolutional Neural Network Properties

Lecture 5: Local Connectivity

Lecture 6: Parameter Sharing

Lecture 7: Pooling & Subsampling


Section 3: Convolution Operation

Lecture 8: Definition of Convolution

Lecture 9: Image Convolution Example

Lecture 10: Other Filters


Section 4: Convolutional Neural Network Layers

Lecture 11: Convolutional Layer

Lecture 12: Strided Convolution

Lecture 13: Strided Convolution with Padding

Lecture 14: Convolution over Volume

Lecture 15: Activation Function (ReLU)

Lecture 16: Pooling Layer

Lecture 17: Convolutional Network

Lecture 18: BatchNormalization Layer


Section 5: Convolutional Neural Network Architectures

Lecture 19: Introduction to CNN Architectures

Lecture 20: LeNet-5

Lecture 21: AlexNet & ZFNet

Lecture 22: VGGNet

Lecture 23: GoogleNet (Inception Network)

Lecture 24: Inception V2, V3, V4, Inception-ResNet-v1, Inception-ResNet-v2

Lecture 25: Xception

Lecture 26: Residual Neural Network (ResNet)

Lecture 27: DenseNet


Section 6:  CNN for Object Detection

Lecture 28: Computer Vision Tasks

Lecture 29: Introduction to Object Localization and Detection

Lecture 30: Classification + Localization

Lecture 31: Object Detection with Sliding Window

Lecture 32: R-CNN

Lecture 33: Fast R-CNN

Lecture 34: Faster R-CNN

Lecture 35: You only look once (YOLO)


Section 7: CNN for Instance Segmentation

Lecture 36: Instance Segmentation

Lecture 37: Mask R-CNN


Section 8: CNN for Semantic Segmentation

Lecture 38: Semantic Segmentation

Lecture 39: Semantic Segmentation with Sliding Window

Lecture 40: Fully Convolutional Network

Lecture 41: Up-sampling with Transposed Convolution

Lecture 42: Fully Convolutional Network: Skipping Connections


What You Will Learn!

  • Deep Learning
  • Convolutional Neural Networks
  • CNN Architectures
  • Convolution Operation
  • Object Detection
  • Semantic Segmentation
  • Instance Segmentation
  • AlexNet VGG Inception GoogleNet ResNet DenseNet
  • R-CNN Fast R-CNN Faster R-CNN
  • Mask R-CNN

Who Should Attend!

  • Computer Science Students: Undergraduate and Master Students
  • Deep Learning Developers
  • Machine Learning Developers
  • Data Scientists
  • Anyone who have a passion in deep learning, machine learning and AI