SOW-MKI75
Applied Machine Learning
Course infoSchedule
Course moduleSOW-MKI75
Credits (ECTS)6
CategoryMA (Master)
Language of instructionEnglish
Offered byRadboud University; Faculty of Social Sciences; Artificial Intelligence;
Lecturer(s)
Examiner
prof. dr. M.A.J. van Gerven
Other course modules lecturer
Contactperson for the course
dr. M. Shahsavari
Other course modules lecturer
Coordinator
dr. M. Shahsavari
Other course modules lecturer
Academic year2023
Period
SEM2  (29/01/2024 to 12/07/2024)
Starting block
SEM2
Course mode
full-time
Remarks-
Registration using OSIRISYes
Course open to students from other facultiesYes
Pre-registrationNo
Waiting listNo
Placement procedure-
Aims
The course in under development yet...
Upon successful completion of the course, the student can:
  • Understand the mathematics behind machine learning algorithms
  • Understand the mathematics behind deep learning algorithms
  • Deploy deep learning models in production
  • Understand and design machine learning procedures algorithms and pipelines
  • Have an understanding of the intrinsic link between probability and statistical machine learning
Content
Introduction to optimization techniques, Gradient descent, Model Selection, Bias-Variance Tradeoff, Gaussian Processes, Bagging, Boosting, Decision Trees. An introduction to data structure optimization, Stochastic Gradient descent and all its variants, batch learning. Automatic differentiation computational graphs and learning optimization , Deep learning, neural networks and backpropagation.
Level
AI-MA
Presumed foreknowledge
Essential knowledge to be able to pass the course::
  • Probability theory, calculus and linear algebra
  • Basic Python programming
  • Basic understanding of computational complexity
  • Basic knowledge of a Unix/Linux operating system
Advised:
  • Measure theory
  • Stochastic calculus
  • Advanced programming and mathematical logic knowledge
Test information
The test will exist of four larger individual assignments

There will be one course grade which is the average of the assignments

Possibility to resit of each type:  Assignments can be handed in again for grading if and only if the original grade was lower than 5.5

Grading for each part is registered in Brightspace, only the final grade is published in Osiris.
 
Specifics
The reading material is non-obligatory where students can go and look for extra material or deeper understanding.
--

Please sign up for any course at (https://portal.ru.nl/home), it is obligatory.

Students who are enrolled for a course are also provisionally registered for the exam. 

Resit: Manual register at (https://portal.ru.nl/home) until five working days prior to the date of the exam. No delayed registration is possible. 

We urge you to always read the course information on Brightspace. 
 
Recommended materials
Book
The Elements of Statistical Learning - available pdf https://web.stanford.edu/~hastie/ElemStatLearn/
Book
All of Statistics: A Concise Course in Statistical Inference
ISBN: 978-1441923226
Author:Larry A. Wasserman
Book
ISBN:978-0195124415
Title:Complexity: A Guided Tour
Author:Melanie Mitchell
Book
ISBN:978-0262039406
Title:Foundations of Machine Learning
Author:Afshin Rostamizadeh, Ameet Talwalkar, and Mehryar Mohri
Book
ISBN:9781449369415
Title:Introduction to machine learning with python
Author:Mueller, Guido
Book
ISBN:9781461468486
Title:Applied predictive modeling
Author:Kuhn, Johnson
Book
ISBN:978-0262035613
Title:Deep Learning
Author:Goodfellow, Bengio, Courville
Book
ISBN:978-0241398630
Title:The Art of Statistics: How to Learn from Data
Author:Spiegelhalter

Instructional modes
Lecture

Work group

Tests
Final grade
Test weight1
Test typeExam
OpportunitiesBlock SEM2, Block SEM2