SOW-MKI49
Neural Information Processing Systems
Course infoSchedule
Course moduleSOW-MKI49
Credits (ECTS)6
Category-
Language of instructionEnglish
Offered byRadboud University; Faculty of Social Sciences; Artificial Intelligence;
Lecturer(s)
Coordinator
prof. dr. M.A.J. van Gerven
Other course modules lecturer
Examiner
prof. dr. M.A.J. van Gerven
Other course modules lecturer
Contactperson for the course
dr. U. Güçlü
Other course modules lecturer
Lecturer
dr. U. Güçlü
Other course modules lecturer
Lecturer
dr. S.C. Quax
Other course modules lecturer
Academic year2018
Period
SEM1  (03/09/2018 to 03/02/2019)
Starting block
SEM1
Course mode
full-time
RemarksOpen to AI, CNS (Brain Networks and Neuronal Communication) and CS (Data Science) Master students
Registration using OSIRISYes
Course open to students from other facultiesYes
Pre-registrationNo
Waiting listNo
Placement procedure-
Aims
After successful completion of the course, students:
  • Know about current advances in modern neural networks such as deep learning, recurrent neural networks, reinforcement learning and generative modeling. 
  • Are able to implement advanced neural networks in the Python programming language.
  • Understand how neural networks can be used to model cognitive processes. 
Content
A main objective of artificial intelligence is to build machines whose cognitive abilities match (or surpass) those of humans. This is also referred to as artificial intelligence.  One way to achieve this goal is by developing cognitive architectures that mimick the algorithms used by our own brains. This success of such an approach relies on a continuous interplay between AI and neuroscience.
 
In this course, we will explore how modern neural networks provide us with the tools to model cognitive processes in artificial systems and understand cognitive processses in biological organisms. 
 
The course consists of different components: 
  • During the lectures, students will get acquainted with the theoretical basis and practical development of advanced neural networks. This will be done via presentation and discussion of key papers.
  • During the practical sessions, students will learn to implement neural network approaches, related to specific papers discussed in class. To this end, the Pyhton programming language will be used.
Levels
AI-MA

Test information
Practical assignments 100%

Prerequisites
• Python programming experience
• Mathematical skills at the AI Bachelor level (probability theory, calculus and linear algebra)
• Basic knowledge of neural networks

Contact information
Prof. dr. M.A.J. van Gerven, T: 024 3652354, E: m.vangerven@donders.ru.nl
Dr. U. Güçlü, T: 024 3611158, E: u.guclu@donders.ru.nl

Recommended materials
Literature list
Selected papers

Instructional modes
Lecture
Attendance MandatoryYes

Practical sessions
Attendance MandatoryYes

Tests
Practicals
Test weight1
Test typeLab course
OpportunitiesBlock SEM1, Block SEM2