Faculty of Engineering - Ain Shams University, Home

Home  >  Faculty of Engineering - Ain Shams University, Home

Deep Learning

What Will Learn?

  • Course Aims
    By the end of the course the students will be able to: • Understand the basic concepts, algorithms and applications of deep learning methods • Understand the basic concepts of building of single and multilayer neural networks • Understand the basic concepts of training single and multilayer neural networks • Understand the basic concepts of generalization and regularization in neural networks • Understand the basic concepts of stacked autoencoders • Understand the basic concepts and training of convolutional neural networks • Understand the basic concepts and training of recurrent neural networks • Understand the basic concepts and training of Restricted Boltzmann machines
  • Course Goals
  • Decent Work and Economic Growth
  • Industry, Innovation and Infrastructure
  • Sustainable Cities and Communities

Requirements

CSE382

Description

  • English Description

    Basic neural networks. Convolutional Neural Networks (CNN): AlexNet, VGG, ResNet. CNN optimization techniques. Recurrent Neural Networks (RNN): LSTM. Generative models: Autoencoders, Generative Adversarial Networks (GANs). Deep reinforcement learning. Applications: Image understanding, Natural language processing, Object detection. Practical engineering tricks for training and fine-tuning networks.
  • Arabic Description

    Basic neural networks. Convolutional Neural Networks (CNN): AlexNet, VGG, ResNet. CNN optimization techniques. Recurrent Neural Networks (RNN): LSTM. Generative models: Autoencoders, Generative Adversarial Networks (GANs). Deep reinforcement learning. Applications: Image understanding, Natural language processing, Object detection. Practical engineering tricks for training and fine-tuning networks.
  • Department
    Computer and Systems Engineering
  • Credit Hours
    3
  • Grades
    Total ( 100 ) = Midterm (25) + tr.Major Assessment (30 = tr.Industry 0% , tr.Project 15% , tr.Self_learning 5% , tr.Seminar 15% ) + tr.Minor Assessment (5) + Exam Grade (40)
  • Hours
    Lecture Hours: 2, Tutorial Hours: 2, Lab Hours: 0
  • Required SWL
    125
  • Equivalent ECTS
    5
  • • Michael Nielsen. Neural Networks and Deep Learning. Determination Press. 2016
  • • Ian Goodfellow, Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press, 2016. - Michael Nielsen. Neural Networks and Deep Learning. Determination Press. 2016.