Deep Learning
Simulating the Human Mind in Thinking
12h 40m64 lectures5 sections
What you'll learn
- Understand deep learning fundamentals
- Learn to implement neural networks
- Apply learning in computer vision
- Manage projects using TensorFlow
- Design advanced models like RNN
- Acquire skills in natural language processing
About this course
Master deep learning from the ground up in this comprehensive course. It covers the fundamentals of neural networks, deep learning concepts, and how to build effective models using tools like TensorFlow. You will explore various practical applications, including deep neural networks, recurrent networks, and predictive models. The course includes hands-on projects and explained code to help you apply deep learning practically.
Expected outcomes
- Master the use of neural networks to build efficient deep learning models.
- Analyze data and apply deep learning to solve complex problems.
- Design and implement real projects using advanced deep learning tools.
- Understand how to optimize model performance using advanced techniques.
- Prepare yourself to enter the field of artificial intelligence and deep learning as a professional.
Course content
1Fundamentals of Deep Learning and Neural Networks
31 lectures
- Introduction1:56
- Neural Network8:13
- Supervised Learning and Neural Networks7:52
- Binary Classification13:55
- Load Symbol List
- Logistic Regression Algorithm8:51
- Cost Function11:43
- Calculate Variable Values14:00
- Calculus13:34
- Computational Graph6:23
- Computational Graph for Derivative Calculation15:24
- Derivative Calculation for Algorithm Application12:51
- Derivative Calculation for Several Examples10:34
- Understanding Directions15:59
- Load Practical Example
- Using Directions in Linear Regression Algorithm14:45
- Distribution in Python14:29
- Load Practical Example
- Introduction to Hollow Neural Network11:08
- Hollow Neural Network Representation and Output Calculation17:30
- Output Calculation for Several Examples10:25
- Activation Function11:23
- Calculus for Activation Functions15:58
- Loading Function Format
- Implementing Gradient Descent for the Hollow Neural Network18:27
- Introduction to Deep Neural Networks11:19
- Forward Propagation in Deep Neural Networks13:52
- How to Calculate Matrix Dimensions22:52
- Core Components for Implementing Deep Neural Networks14:14
- Implementing Core Components for Gradient Descent Calculation11:22
- Hyperparameters4:44
2Developing Deep Neural Networks and Training Models
6 lectures
- Libraries Used for Development7:08
- Practical Example of Using Keras Library for Prediction11:12
- First Practical Application26:35
- Loading Data File
- Practical Example of Using Keras Library for Classification13:51
- Second Practical Application35:06
3Using TensorFlow
9 lectures
- Introduction to TensorFlow16:13
- Fundamentals Part One9:04
- Fundamentals Part Two17:50
- Fundamentals Part Three9:00
- Application on Prediction Part One21:33
- Application on Prediction Part Two26:13
- Download Data File
- Application on Classification Part One32:22
- Application on Classification Part Two24:28
4Convolutional Neural Network
8 lectures
- Introduction to Convolutional Neural Networks7:54
- Basic Principles5:46
- Architecture of Convolutional Neural Networks18:26
- Practical Application Using Traditional Method Part One27:20
- Practical Application Using Traditional Method Part Two14:01
- Download the Application
- Practical Application on the Convolutional Neural Network29:50
- Download the Application
5Building Different Models for Deep Learning
10 lectures
- Introduction to Building Different Models for Deep Learning4:45
- Time Series Data3:06
- Recurrent Neural Network6:48
- LSTM Model6:45
- Practical Application of LSTM Model Basics23:14
- Download the Application
- Introduction to New Autoencoders5:20
- Architecture of Autoencoders4:02
- Practical Application on Autoencoders19:13
- Download the Application
Instructor
Eng. Amr Abdel Fattah
6,563 students20 courses
This course is part of the diploma
