خصم 50% على دورة ال DEEP LEARNING باستخدام البايثون لفترة محدودة
اضافة الى المفضلة١٥٠ دينار
دورة Deep Learning, Image Processing and Classification باستخدام Python
دورة شاملة عملية تطبيقية على البايثون خاصة بطلاب الدراسات العليا والباحثين مع دكتور متخصص متواجد في المانيا ..
خصم عالسعر الى النصف خلال شهر3 اصبح 150 دينار اردني بدلا من 300 دينار اردني
يمكن لاي طالب في أي مكان التسجيل بالدورة #اونلاين, وسيكون بالدورة كما لو أنه في نفس القاعة!
*عدد ساعات الدورة : حوالي 30 ساعة
المحاضرة الاولى : 11-4-2020
للتسجيل او الاستفسار :
Call/Whatsapp: 00962795037290
info@atitgroup.com
Skype : ATITAcademy
محتوى الدورة بالتفاصيل :
This comprehensive course will be covered over 9 sessions as detailed below:
1) Introduction to Artificial Intelligence and Deep Learning
- What is Artificial Intelligence (AI) - What is Deep Learning (DL) - Types of DL:
• Convolution Neural Network (CNN)
• Recurrent Neural Network (RNN)
• Long Short Term Memory (LSTM)
• Reinforcement Learning (RL) and Deep Q-Network (DQN)
• Generative Adversarial Network (GAN)
- Applications on DL
- Operations of DL
- Practical Examples
2) Introduction to Python
- Python Basics
- Installing Python
- PIP packages installer
- Python Variables
- Input and Output
- If...Then...Else
- Loops
- Collections
- Functions
- Error Handling
- Practical Project
3) Python for Deep Learning and Image Processing
- Data Manipulation
- Normalizing data
- Formatting data
- Important Python Packages for Image Processing and Deep Learning:
• OpenCV
• Tensorflow
• Keras
• Dlip
- Practical Project
4) Optimization
- Optimization Overview
- DL as an optimization problem
- Types of Optimizers (Teachers)
- Optimization Approach Components
- Formulating an Objective Function
- Solving a maximization problem
- Solving a minimization problem
- Producing Convergence Curve
- Practical Project on real functions
5) DNN Layers, Activation and Loss Functions - Input Layer - Hidden Layer:
- Convolution Layers
- Max pooling Layers
- Classification Layer
- Output Layer
- Dropout Layer - Fully Connected Layers - Activation Functions:
• RELU
• Sigmoid
• Softmax
- Loss Functions:
• Mean Square Error
• Cross-Entropy Loss
- Practical Project
6) Data Preparation - Data Labeling:
• Region of Interest (Bounding Box)
• Class (Group)
• Semantic labeling
- Multi Class vs Multi Label
- Data Normalization - Batching Data - Data Splitting:
- Training Dataset
- Validation Dataset
- Testing Dataset
- Cross Validation
- Data Preparation Complete Project
7) Computer Vision and Image Processing
- Image Formation and Representation
- Geometric Transformation
- Image Registration
- Image Clustering
- Background and Foreground Objects - Edge Detection - Feature Descriptors:
• The histogram of oriented gradients (HOG)
• SIFT
• SURF
- Image Processing Complete Project
8) Clustering and Classification
- Clustering Vs Classification
- Image Classification in details
- CNN in details
- Images Classification Project 1 (General Dataset)
- Images Classification Project 2 (Medical Dataset)
9) Real-Time Face Detection
- Working with video and frames
- Viola-Jones method
- Face Detection
- Face Landmarks
- Facial Expression Recognition
- Project 1: Face Detection
- Project 2: Expression Recognition
- Project 3: Data Generation using GANs
حيث أننا قدمنا من قبل ورشة عمل مكثفة في هذا المجال ( بإمكانكم مشاهدة الورشة كاملة على قناة اليوتيوب ATIT Academy )
