كلية الهندسة - جامعة عين شمس, الرئيسية

الرئيسية  >  كلية الهندسة - جامعة عين شمس, الرئيسية

Introduction to Machine learning

What Will Learn?

  • Course Aims
    - Train students on the fundamental principles of machine learning methods - Provide students with the basic concepts of the different learning methods - Develop the students’ knowledge of the architectural techniques used to design and build learning models - Train students to evaluate quantitatively the performance of any machine learning model - Train students to be able to explain the performance of machine learning models - Develop the student's knowledge of the motivation of the shift to automated machine learning
  • Course Goals
  • Decent Work and Economic Growth
  • Industry, Innovation and Infrastructure
  • Sustainable Cities and Communities

Requirements

PHM113 AND CSE141

Description

  • English Description

    Introduction to Machine Learning: Learning paradigms, Algorithms, Theoretical results, Applications. Basic concepts in machine learning and methods: Bayesian classification, Logistic regression, Nearest neighbor classifier. Decision trees, Bias and the trade-off of variance, Regression (linear and nonlinear), Support Vector Machines (SVMs), Artificial neural networks, Ensemble methods, Dimensionality reduction, Clustering algorithms. Principle component analysis, Reinforcement learning.
  • Arabic Description

    Introduction to Machine Learning: Learning paradigms, Algorithms, Theoretical results, Applications. Basic concepts in machine learning and methods: Bayesian classification, Logistic regression, Nearest neighbor classifier. Decision trees, Bias and the trade-off of variance, Regression (linear and nonlinear), Support Vector Machines (SVMs), Artificial neural networks, Ensemble methods, Dimensionality reduction, Clustering algorithms. Principle component analysis, Reinforcement learning.
  • قسم
    هندسة الحاسبات والنظم
  • الساعات المعتمدة
    3
  • الدرجات
    الإجمالي ( 100 ) = نصف العام (25) + tr.Major Assessment (30 = tr.Industry 0% , tr.Project 20% , tr.Self_learning 5% , tr.Seminar 10% ) + tr.Minor Assessment (5) + درجة الامتحان (40)
  • الساعات
    ساعات المحاضرة: 2, ساعات التعليم: 2, ساعات المعمل: 0
  • Required SWL
    125
  • Equivalent ECTS
    5
  • Pattern Recognition, Sergios Theodoridis and Konstantinos Koutroumbas , Fourth Edition , Academic Press, 2009.
  • Pattern Classification, Richard O. Duda, Peter E. Hart and David G. Stork, Second Edition, Wiley Press, 2000.
  • Pattern Recognition and Machine Learning by C. Bishop, Springer 2006.