Join us at the next MRM with talks from PhD students Pablo Alejandro de Abreu Urbizagastegui and Yeshwanth Bethi on Spiking Neural Networks
Topic: Predictive Processing on Neuromorphic Hardware Speaker: Pablo Alejandro de Abreu Urbizagastegui
Predictive Processing theory has become a hot topic in the study of neural networks. It gives us clues about how the neocortical circuitry processes information and optimizes learning, but unfortunately, the understanding of the implementational level in the cortex is still lacking. In this talk, I will discuss how a neuromorphic processor developed at ICNS could benefit from this theoretical framework. I will also present basic building blocks that could be used to implement it in a simplified, biologically plausible manner.
Topic: Abstraction of Spiking Neural Networks Speaker: Yeshwanth Bethi
The field of Machine learning has seen tremendous progress in the last decade due to the success of Artificial Neural Networks and error backpropagation. But evidence shows us that error backpropagation is not feasible in biology. Though Spiking Neural Networks (SNN) have long been described as the third generation of neural networks, training SNNs is still an open research question. In this talk, I would like to present the motivation to find novel abstractions to SNN models which can help investigate learning rules in SNNs.
We thank you for your continued attendance at the MRM's and look forward to seeing you again.
MARCS staff and students are reminded that all meetings and workshops have an important role in building and maintaining the sense of community which is central to the success of MARCS as a cooperative and energetic research institute. Your attendance is both welcomed and expected.
Disclaimer: MRM meetings may be recorded on Zoom for future access to MARCS members and subject to speaker's approval
