DT8807 - Advanced Topics in Deep Learning with Python


Examination arrangement

Examination arrangement: Portfolio
Grade: Passed / Not Passed

Evaluation Weighting Duration Grade deviation Examination aids
Portfolio 100/100

Course content

In this course you will learn about the purpose of machine learning, where and how to apply it in the real world. You will learn fundamentals of machine learning such as supervised learning, unsupervised learning, feature engineering, model selection, training modes, and model evaluation. You will learn how to develop your machine learning pipeline in Python using sklearn, kears and pytorch. In this course, you will add new skills and new competence to your portfolio including regression, classification, clustering, and time series prediction. You will master skills of training deep neural nets such as CNN, RNN for images, videos, text, and time-series. You will learn about advanced deep learning architectures and transfer learning.

Learning outcome

Upon Completion of This Course, You'll Have:

  1. An understanding of the capabilities and limitations of machine learning (ML), and the knowledge of how to formulate your problem to solve it effectively.
  2. An understanding of convolution neural nets, recurrent neural nets, and state-of-the-art transfer learning models.
  3. An effective process for developing your machine learning pipeline to tackle real world problems such as machine vision, text understanding and time series prediction.
  4. The skills required to deploying, monitoring, and evaluating the ML model, as well as assessing its relevance, and the uses of different ML models.
  5. The basis required to collect, process, and utilize data efficiently.
  6. The basic skills required to select the right platform to deploy your model (cloud, edge device, hybrid) and how to configure it to achieve the required performance.
  7. The ability to document and communicate the results of your ML approach and guide your coding and ML efforts in the right direction.

Learning methods and activities

  • Teaching approach: 5 hours each (lectures - practice - project work).

Further on evaluation

Evaluation: exam will be in the form of a portfolio assessment where samples of work and mini projects will be used to evaluate the intended learning outcomes (ILOs) achievement throughout the course. The portfolio contains assignments that are carried out, digitally documented and submitted during the term. Both individual and team assignments may be given. Assignments are designed to help students achieve specific course learning outcomes, and formative feedback is given during the period of the portfolio. Pass/Fail: it is required to achieve 70/100 points or 70 % in order to pass.

Course materials

An updated reading list will be provided before the course. To name but a few:

  • Josh Patterson and Adam Gibson (2017). Deep learning: a practitioner’s approach. O'Reilly.
  • Andreas C. Muller and Sarah Guido (2017). Introduction to machine learning with python. O'Reilly.
  • Mohamed Elgendy (2020). Deep learning for vision systems. O'Reilly.

More on the course



Version: 1
Credits:  7.5 SP
Study level: Doctoral degree level


Term no.: 1
Teaching semester:  SPRING 2023

Language of instruction: English

Location: Ålesund

Subject area(s)
  • Computer and Information Science
Contact information
Course coordinator:

Department with academic responsibility
Department of ICT and Natural Sciences


Examination arrangement: Portfolio

Term Status code Evaluation Weighting Examination aids Date Time Examination system Room *
Spring ORD Portfolio 100/100 INSPERA
Room Building Number of candidates
  • * The location (room) for a written examination is published 3 days before examination date. If more than one room is listed, you will find your room at Studentweb.

For more information regarding registration for examination and examination procedures, see "Innsida - Exams"

More on examinations at NTNU