Artesis Plantijn Hogeschool Antwerpen
Wetenschap en Techniek
campus Spoor Noord Ellermanstraat
Ellermanstraat 33 - 2060 Antwerpen
wt@ap.be
AI Principles32318/2199/2122/1/04
Study guide

AI Principles

32318/2199/2122/1/04
Academic year 2021-22
Is found in:
  • Bachelor of Applied Computer Science, programme stage 2
    Programme option:
    • Big Data
This is a single course unit.
Study load: 3 credits
It is not possible to enrol in this course unit under
  • exam contract (to obtain a credit).
  • exam contract (to obtain a degree).
Teaching staff: Haddouchi Hassan
Teaching staff are not (all) known yet.
Languages: Dutch
Scheduled for: Semester 1
This course unit is marked out of 20 (rounded to an integer).
Possible deadlines for learning account: 15.10.2021 ()
Re-sit exam: is possible.
Possibility of tolerance: This course unit is eligible for tolerance according to the criteria as determined by the degree programme you are enrolled in.
Total study time: 78,00 hours

Prerequisites

There are no prerequisites for this course.

Learning outcomes (list)

A.6. Application Design
Understand the basic principles of ML
Recognizes the difference between supervised and unsupervised learning
Understands the fundaments of deep learning
Recognizes the basic principles of data training and cross validation
B.1. Design and Development
Adopts the correct principles to explore, handle (e.g. melting, merging, ...) and clean the data
Understand the basic principles of ML
Recognizes the difference between supervised and unsupervised learning
Understands the fundaments of deep learning
Recognizes the basic principles of data training and cross validation
Can visualize complex data using modern visualization tools
Correctly reports on a ML analysis
Develops a AI strategy bases on a problem statement
B.3. Testing
Evaluates the performance of an algorithm in a suitable way.
E.3. Risk Management
Recognizes the risks of incomplete and inaccurate data
Task analysis
Develops an analysis project to make predictions on future data based on rough data and a phrasing of a question.
Evaluates the performance of an algorithm in a suitable way.
Works in team on a common analysis project.
Strategic action
Develops a AI strategy bases on a problem statement
Written communication
Communicates the results of an analysisproject in a proper and clear way.
Correctly reports on a ML analysis

Educational organisation (list)

Learning Activities
Lectures and / or tutorials12,00 hours
Practicum24,00 hours
Work time outside of contact hours42,00 hours

Evaluation (list)

Evaluation(s) for first exam chance
MomentForm%Remark
Academic yearContinuous skills assessment hands on (Permanent evaluation)30,00casus: momentopname op examen, digitaal
Academic yearKnowledge test30,00Open en gesloten vragen : momentopname op examen, digitaal
Evaluation(s) for re-sit exam
MomentForm%Remark
2nd examination periodKnowledge test30,00Open en gesloten vragen : momentopname op examen, digitaal
2nd examination periodSkills assessment hands on30,00casus: momentopname op examen, digitaal
Evaluation(s) for both exam chances, not reproducible in re-sit exam
MomentForm%Remark
Academic yearContinuous skills assessment hands on (Permanent evaluation)40,00Casus : permanent uitgesteld