In recent years various learning algorithms for spike-based neural networks have been proposed including Hebbian learning and spike-timing dependent plasticity (STDP). At the same time the behavior of state-changing memristive devices shows promissing results for their integration in neural networks.
In this project we seek to advance the implementation of stochastic memristive devices as synaptic building blocks and their ability to reproduce learning models. Based on models obtained from physical devices you will simulate neural networks consisting of memristive devices and integrate-and-fire neurons. Different network topologies and learning performances will be evaluated on common machine learning tasks.
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.
- Required skills (e.g. mandatory courses, if required)
* good programming skills in Python
* basic knowledge of spiking neural networks
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.