•   Advanced Topics in Embedded Software 5051214-3003 02.09.2020-05.03.2021  15 credits  (PTIVIS17S) +-
    Competence objectives of study unit
    After completing the course, the student:can apply modern design methods and tools in embedded software design.has up-to-date knowledge on current topics in embedded software
    Content of study unit
    The course covers current topics in embedded software. See implementation plan for details.

    Teacher(s) in charge

    Mojtaba Jafaritadi

    Learning material

    1) Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems 2nd Edition by Aurélien Géron, OREILLY, 2020

    2) Hands-on Scikit-Learn for Machine Learning Applications, by David paper, Apress publications, 2020

    3) Guide to intelligent data analysis: how to intelligently make sense of real data. by Berthold, Michael R., et al. Springer Science & Business Media, 2010.

    Learning methods

    The course includes theoretical lectures, mandatory practical lab works, self-study/ home assignments, and a final project work.

    NOTE: Due to the current pandemic, remote implementation of the lab works is still one possibility, so be prepared for last notice changes.

    Objects, timing and methods of assessment

    Must pass Final Exam:
    60% -> 1
    68% -> 2
    76% -> 3
    84% -> 4
    92% -> 5
    Mandatory lab works: individual Lab performance matters
    Mandatory lectures
    Mandatory project work (failure in delivery= failed)

    Teaching language

    English

    Timing

    02.09.2020 - 05.03.2021

    Enrollment date range

    02.07.2020 - 02.09.2020

    Group(s)
    • PTIVIS17S
    Seats

    0 - 42

    Responsible unit

    Engineering and Business

    Small group(s)
    • Group A (Size: 42.
    Teachers and responsibilities

    The lectures cover the main theories, techniques, and algorithms in machine learning and basics of deep learning, starting with fundamental concepts such as regression/classification and ending up with more advanced topics such as artificial neural networks and model selection and performance estimation. The main goal is to extend context and background knowledge around AI, machine learning, and deep learning.

    The course in general gives an overview of many machine learning and deep learning methods that can be used to build models and systems based on observed data. After the course, students should understand the main principles of machine learning and pattern recognition methods and steps needed for applying them in real applications. The student especially learns the core concepts of classification, gradient descent, model evaluation, overfitting, and underfitting and is able to find a suitable balance between these extremes in a given problem at hand.

    Campus

    Kupittaa Campus

    Assessment scale

    H-5

    Exam dates and retake possibilities

    Exam dates will be announced (it would be most likely the next session after the last lecture)

    Pedagogic approaches

    Lectures (onsite and online lectures will be arranged)
    Self-study materials from online sources
    Project work (will be discussed during the course)
    Exam (the date will most likely the next session after the last lecture in December.)

    Student's schedule and workload

    lab works 12x3h = 36h
    lectures 14x2h = 28h
    exam =4h
    exam preparation 32h
    TOTAL 100h

    Content scheduling

    Chapter 1: The Machine Learning Landscape
    Chapter 2: End-to-End Machine Learning Project
    Chapter 3: Classification
    Chapter 4: Training Models
    Chapter 5: Support Vector Machines
    Chapter 6: Decision Trees
    Chapter 7: Ensemble Learning and Random Forests
    Chapter 8: Dimensionality Reduction
    Chapter 9: Unsupervised Learning Techniques
    Chapter 10: Introduction to Artificial Neural Networks with Keras
    Chapter 11: Training Deep Neural Networks
    Chapter 12: Custom Models and Training with TensorFlow
    Chapter 13: Loading and Preprocessing Data with TensorFlow
    Chapter 14: Deep Computer Vision Using Convolutional Neural Networks
    Chapter 15: Processing Sequences Using RNNs and CNNs