Calendar

Previous Seminars & Events: 

Typically, meetings are on Fridays and start at 12:30 in the colloquium room (00.832) of the Department of Biophysics (Huygens Building, Radboud University), unless listed otherwise.

Schedule is due to changes—you might want to follow us on Twitter to be alerted when such a change occurs.

You may also be interested in the ICIS AI-group colloquia at the computer-science department, typically friday afternoon.

ICIS calendar

For more information about the seminars please contact Wim Wiegerinck at

Contact Us

SNN: Seminar

Nijmegen, Heyendaalseweg 135, 00.832

Fri, 7-Apr-2017 11:30-13:00

SNN: Seminar

Nijmegen, Heyendaalseweg 135, 00.832

Fri, 14-Apr-2017 11:30-13:00

SNN: Seminar

Nijmegen, Heyendaalseweg 135, 00.832

Fri, 21-Apr-2017 11:30-13:00

SNN: Seminar

Nijmegen, Heyendaalseweg 135, 00.832

Fri, 28-Apr-2017 11:30-13:00

SNN: Seminar

Nijmegen, Heyendaalseweg 135, 00.832

Fri, 5-May-2017 11:30-13:00

SNN: Seminar

Nijmegen, Heyendaalseweg 135, 00.832

Fri, 19-May-2017 11:30-13:00

SNN: Seminar Sander Bohte

Title: Fast and Efficient Deep Spiking Neural Networks Biological neurons communicate with a sparing exchange of pulses -- spikes. It is an open question how real spiking neurons produce the kind of powerful neural computation that is possible with deep artificial neural networks, using only so very few spikes to communicate. Building on recent insights in neuroscience, we present an Adapting Spiking Neural Network (ASNN) based on adaptive spiking neurons. These spiking neurons efficiently encode information in spike-trains using a form of Asynchronous Pulsed Sigma-Delta coding while homeostatically optimizing their firing rate. We show that this type of network is inherently able to carry out asynchronous and event-driven neural computation, while performing identical to corresponding artificial neural networks (ANNs) on hard pattern and image recognition taks. In particular, we show that these adaptive spiking neurons can replace analogue artificial neurons in standard feedforward ANNs comprised of such units, provided we map the spiking neuron's transfer function. We show that this approach works for both standard feedforward and convolutional neural networks and also restricted memory-based networks. We show that the developed ASNN outperforms current Spiking Neural Networks (SNNs) implementations, while responding up to an order of magnitude faster and using an order of magnitude fewer spikes.

Nijmegen, Heyendaalseweg 135, 00.832

Mon, 22-May-2017 11:00-12:30

SNN: Seminar

Nijmegen, Heyendaalseweg 135, 00.832

Fri, 2-Jun-2017 11:30-13:00

SNN: Seminar Jonas Teuwen

Nijmegen, Heyendaalseweg 135, 00.832

Fri, 16-Jun-2017 11:00-12:30