This project aims at setting up a framework for spiking (= event-based) reinforcement learning. The target problem is to learn how to play Pong. Different neuromorphic hardware accelerators (e.g. SpiNNaker, Spikey) will be used, and the ultimate goal is to let these accelerators compete in the game.
The project will make heavy use of the C++ programming language. The possibility to showcase the running game on an 8x8x8 RGB LED cube exists, depending on the preferences of the students and the progress in the project.
Please note that the teams will be selected by the supervisors on the basis of short applications that students are expected to send to them. Registering to the project in the ekVV will only be regarded as expression of interest; it will not secure a team membership. Please get in touch with the supervisors for information on the application procedure.
Students should be familiar with the C++ programming language.
Prior knowledge about neural networks, especially spiking neural networks, is beneficial, but not mandatory.
Frequency | Weekday | Time | Format / Place | Period |
---|
Module | Course | Requirements | |
---|---|---|---|
39-M-Inf-GP Grundlagenprojekt Intelligente Systeme | Gruppenprojekt | Ungraded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.