التعـلــم العمــيــق باسـتـخــدام بــايـثــون
Deep Learning using Python

Course Overview:

This course provides students with a comprehensive introduction to Deep Learning (DL) using Python, focusing on both theoretical foundations and practical applications. Students will learn how to design, train, and evaluate deep neural networks using Python libraries, gaining hands-on experience in solving real-world problems. 

Learning Objectives:

By the end of this course, students will be able to:

• Design and implement deep learning models using Python frameworks.

• Apply deep learning techniques to diverse domains, including image recognition, natural language processing, and predictive analytics.

• Build a strong foundation for advanced research and professional applications in artificial intelligence.

What You Will Learn:

• Introduction to Deep Learning – understanding neural networks, perceptrons, and the difference between ML and DL.

• Neural Network Fundamentals – concepts of layers, weights, biases, activation functions, and loss functions.

• Training Deep Neural Networks – gradient descent, backpropagation, and optimization techniques.

• Regularization and Optimization – dropout, batch normalization, and advanced optimizers such as Adam and RMSprop.

• Convolutional Neural Networks (CNNs) – architectures for image classification and computer vision tasks.

• Recurrent Neural Networks (RNNs) – sequence modeling and applications such as text and speech processing.

• Long Short-Term Memory (LSTM) and GRU Networks – handling long-term dependencies in sequential data.

• Transfer Learning and Pretrained Models – leveraging existing models such as VGG, ResNet, and BERT.

• Generative Models – introduction to Autoencoders and Generative Adversarial Networks (GANs).

• Python Deep Learning Libraries – practical implementation using TensorFlow, Keras, and PyTorch.

• Capstone Project – developing and presenting a deep learning solution for a real-world dataset.