Scribd Logo
Upload

Welcome to Scribd!

  • 14 views

    Course Syllabus - Spring Semester 2022/2023 DS 14350 Computer Architecture For Machine Learning

    Uploaded by

    ggttff
    This course syllabus outlines a 3 credit, required machine learning course offered in the spring semester at Princess Sumaya University. The course will provide an introduction to foundational machine learning algorithms and their applications through lectures, assignments, and exams. Topics include supervised learning techniques like linear regression, classification, and neural networks, as well as unsupervised learning and reinforcement learning. Students will implement algorithms and apply them to real-world problems to develop an understanding of machine learning.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Course Syllabus - Spring Semester 2022/2023 DS 14350 Computer Architecture For Machine Learning

    Uploaded by

    ggttff
    14 views3 pages
    This course syllabus outlines a 3 credit, required machine learning course offered in the spring semester at Princess Sumaya University. The course will provide an introduction to foundational machine learning algorithms and their applications through lectures, assignments, and exams. Topics include supervised learning techniques like linear regression, classification, and neural networks, as well as unsupervised learning and reinforcement learning. Students will implement algorithms and apply them to real-world problems to develop an understanding of machine learning.

    Original Title

    14350_2_710_33328

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This course syllabus outlines a 3 credit, required machine learning course offered in the spring semester at Princess Sumaya University. The course will provide an introduction to foundational machine learning algorithms and their applications through lectures, assignments, and exams. Topics include supervised learning techniques like linear regression, classification, and neural networks, as well as unsupervised learning and reinforcement learning. Students will implement algorithms and apply them to real-world problems to develop an understanding of machine learning.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    14 views3 pages

    Course Syllabus - Spring Semester 2022/2023 DS 14350 Computer Architecture For Machine Learning

    Uploaded by

    ggttff
    This course syllabus outlines a 3 credit, required machine learning course offered in the spring semester at Princess Sumaya University. The course will provide an introduction to foundational machine learning algorithms and their applications through lectures, assignments, and exams. Topics include supervised learning techniques like linear regression, classification, and neural networks, as well as unsupervised learning and reinforcement learning. Students will implement algorithms and apply them to real-world problems to develop an understanding of machine learning.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    Princess Sumaya University for Technology

    King Hussein School for Computing Sciences


    Data Science Department
    Course Syllabus – Spring Semester 2022/2023
    DS 14350 Computer Architecture for Machine Learning

    1. Course Information
    Catalog This course will give an undergraduate-level introduction to machine
    Description learning providing the foundations for mathematical models and algorithms
    required for machine learning tasks and their applications. Topics will include
    supervised learning, unsupervised learning, deep learning, and
    reinforcement learning. This course will put an emphasis on practical
    applications of machine learning in artificial intelligence such as computer
    vision, data mining, speech recognition, text processing and bioinformatics.
    Credit Hours 3
    Prerequisite DS 14330 (Artificial Intelligence)
    Course Type Lecture
    Required/Elective Required
    Textbooks Book1: An Introduction to statistical Learning, By James, Witten, Hastie and
    Tibshirani, 2nd edition 2021, ISBN-13: 978-1071614174. Available online free
    https://www.statlearning.com
    Book2: Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow
    by Aurélien Géron, O’Reilly 2019, ISBN-13: 978-1492032649

    References Reinforcement Learning: An introduction, By Sutton and Barto, 2nd Edition


    MIT Press, Cambridge, MA, 2018, ISBN-13: 978-0262039246
    Instructor Dr. Serin Atiani
    Class Schedule Section1: Mon-Wed 12:30-2:00PM , section2: Mon-Wed 9:30-11:00AM
    Class Location 207
    Office Hours 11-12 weekdays

    2. Course Contents
    Chapter in Chapter in
    Week Topic(s)
    Book1 Book2
    1 Linear algebra revision
    Supervised Learning
    Linear regression, single variate model, gradient descent,
    2 Ch 3.1 Ch 4
    normal equation
    3 Multivariate and nonlinear regression Ch 3.2, 3.3 Ch 4
    4 Classification: Logistic regression Ch 4.1, 4.3 Ch4
    5 Regularization, cross validation, feature selection Ch 5, Ch Ch4
    6.5
    First Exam
    Ch 12.1,
    6 Principal component analysis Ch8
    12.2
    7-8 Large margin classifier, support vector machines Ch 9 Ch5
    Neural Networks
    Ch 10.1, Ch10,
    8-10 Neural networks, backpropagation algorithm
    10.2 Ch11
    Second Exam
    11-12 Convolutional neural networks Ch10.3 Ch14
    13 Recurrent neural networks Ch 10.5

    Sutton
    14-15 Reinforcement learning
    Barto Ch1,3

    3. Course Learning Outcomes


    Upon completion of this course, students will be able to:
    • Develop an understanding of basic machine learning algorithms, their efficient
    implementations and their applicability to different tasks
    • Implement machine learning algorithms and checking their correctness
    • Optimize the models learned and report on the expected accuracy that can be achieved
    by applying the models
    • Apply the algorithms to a real-world problem,

    4. Assessment Policy:
    • First Exam: 20 points
    • Second Exam: 20 points
    • Semester work: 20 points
    • Final exam: 40 points

    5. Contribution of the Course to the Professional Component


    Data Science Topics 100%
    General Education 20%
    Mathematics & Basic Sciences 40%

    6. Expected level of proficiency from students entering the course


    Mathematics Medium
    Physics Not applicable
    Technical writing Some
    Computer programming Proficient

    2
    7. Material available to students, instructors, TAs, and department at end of course
    Students Department Instructors TA(s)
    Course objectives and outcomes form X X X
    Lecture notes, homework assignments X X X
    Samples of homework solutions from 3 X
    students
    Samples of exam solutions from 3 students X

    You might also like