Hopp til hovedinnhold

Deep learning E-MDS120

Deep Learning is a subset of Machine Learning which is completely based on artificial neural networks. As neural networks are designed to mimic the human brain, deep learning is likewise a human brain mimic. These neural networks are made up of a simple mathematical function that can be stacked on top of each other and arranged in the form of layers, giving them a sense of depth, hence the term Deep Learning.

Publisert: Endret:
Facts
ECTS

5

Next course

Autumn 2022

Level

Master

Application deadline

15.06.2022

Teaching method

Online

Course fee

Free of charge, except for course material.

Course content

Illustrasjon på digitalt samfunn

Deep learning has a plethora of applications in almost every field such as health care, finance, and image recognition. It can be used to solve any pattern recognition problem and without human intervention. There are several popular and widely used deep learning frameworks which help to build neural network models. Some of the common ones are Tensorflow, Keras, Pytorch, and DL4J. In this course, in addition to getting a solid understanding of deep learning, you will get hands-on experience by solving practical, real-life tasks using state-of-the-art techniques and software frameworks from machine learning, and deep learning.

Concepts covered in this course provides relevant theoretical and hands-on programming knowledge.

  • Deep Learning - an introduction, and a review of fundamental learning techniques
  • Feedforward neural network
  • Training Neural Network
  • Deep Learning- Recurrent Neural Network, training deep models
  • Probabilistic Neural Network
  • Deep Learning research and applications
  • Deep Learning Tools

Learning outcome

After taking this course, you will

  • have a firm understanding of the most fundamentals of modern neural networks and their practical use
  • Identify the deep learning algorithms which are more appropriate for various types of learning tasks in various domains.
  • Implement deep learning algorithms and solve real-world problems.

Teaching

  • Teaching language: English
  • Weekly lectures published as videos
  • Two hands-on use-case based assignments will be assigned to the students
  • Three/ Four live sessions will be conducted to discuss the solutions for each assignment
Start: Monday, August 22 
  • Weekly videos will be published each Monday 
  • Assignment #1  
    • Start: September 12 
    • 1. Live discussion September 19 
    • 2. Live discussion October 03 
    • End: October 10 
  • Assignment #2  
    • Start: October 17 
    • 1. Live discussion October 24 
    • 2. Live discussion November 07 
    • End: November 14 

Examination

  • The Two assignments are mandatory - approved / not approved
  • Submissions should provide coding solutions to the respective problems with proper documentation
  • Individual home exam. [Grade: pass/fail]
  • Exam date: November 21

Admission requirements

  • Bachelor Degree 180 ECTS
  • Foreign applicants must also document education and English skills in accordance with NOKUT's regulations.

Formal prerequisite knowledge

  • Good programming knowledge
  • Knowledge of basic algebra, probability, and statistics
  • Python Programming Knowledge

Syllabus

  • The syllabus are the lecture slides with references.

Lecturer

Førsteamanuensis
51834507
Det teknisk- naturvitenskapelige fakultet

Institutt for data- og elektroteknologi

Administrational contact persons

Førstekonsulent
51831501
Divisjon for utdanning

UiS etter- og videreutdanning
Senior rådgiver
51833046
Divisjon for utdanning

UiS etter- og videreutdanning