Neural Information Processing

Machine Intelligence 1 (supervised methods)

For the Winter Semester WS 23/24:

  • The course and exam will be offered in an in-person format on-campus.
  • Remote online exams will not be possible.
  • Our ISIS course will be made available in October.

General information

  • The courses Machine Intelligence I and II can be heard independently. You do not have to take one in order to take the other.
  • Machine Intelligence I is offered in the winter while Machine Intelligence II is offered in the summer.
  • The lecture and tutorials are held in English.
  • The course is open to TU students as well as exchange students and visiting students. Non-TU students should apply to a Neben-/Gasthörschaft to gain access to the course material. Please fill out the relevant form with your information and send it to Prof. Obermayer by E-mail before getting the signature from Faculty IV.
  • No formal registration is required to attend the course. The registration is only relevant for the exam.
  • The exam registration procedure will be described in a video on our ISIS course before the first lecture. Prior registration/reservation is not possible and not necessary.
  • Detailed information regarding the material, tutorials and the exam can be found on the ISIS course (see panel on the right). The ISIS course will be made available in October.



Topics covered

  • Connectionist neuron
  • Feed-forward neural networks
  • Learning and generalization
  • Deep Learning
  • Recurrent neural architectures
  • Radial basis function networks
  • Elements of statistical learning theory
  • Structural risk minimization
  • Support vector machines
  • Uncertainty and inference
  • Bayesian networks
  • Bayesian Inference and Neural Networks
  • Reinforcement learning



Prerequisites

  • Solid mathematical knowledge: analysis, linear algebra, probability calculus and statistics. We emphasize this requirement because the course deals with the theoretical aspects and mathematical formulations of the learning algorithms.
  • Basic programming skills, preferably Python, R, Matlab, or Julia. The programming skills are relevant for solving the programming exercises.

Target Audience/Assessment and Grading

ProgramForm of Assessment
MSc in Computational NeuroscienceThe two courses (Machine Intelligence I and II) form a single module (12 ECTS).
assignments & oral exam
MSc in Computer ScienceEach of the two courses (Machine Intelligence I or II) can be taken as a separate module (6 ECTS).
written exam (no assignments during the course)
Other study programs (e.g., mathematics, natural, and engineering sciences)Each of the two courses (Machine Intelligence I or II) can be taken as a separate module (6 ECTS).
written exam (no assignments during the course)

Course Information

CreditsTimeLecturerRoomLanguage
2 SWS Lecture
0434 L 866
Fri 8-10Prof. Dr. Klaus ObermayerH 0110English
2 SWS TutorialThu 8-10,
(Thu 11-13)*
StrömsdörferBH-N 243,
(BCCN seminar room
HU Campus)*
English
*for CNS Students only