Organizers: | |
|---|---|
Abstract: | In this session, we will discuss theoretical frameworks for building principled neuromorphic algorithms. How can these frameworks contribute to a language to formalize and optimize neuromorphic computing algorithms? How can neuromorphic algorithms be systematized, modularized, combined and reused? Due to time, please only ask understanding questions during and between talks, and save questions for the general discussion at the end. |
Speakers | 8:00-8:10: Friedrich Sommer: Sparse VSA as conceptual framework for neuromorphic computing 8:10-8:20: Paxon Frady: Frameworks for efficient coding and computation on neuromorphic hardware 8:20-8:30: Gregor Schöner: Dynamic Field Theory as a theoretical framework for neuromorphic embodied cognition 8:30-8:40: Christian Tetzlaff: The usage of on-chip learning for universal computing 8:40-8:50: Hyeryung Jang: Information-Theoretic Principles for Neuromorphic Computing: Information Bottleneck and Bayesian Learning 8:50-9:00: General Discussion and Questions |
Reference material | Videos: Neuromorphic nearest neighbors: Paxon’s talk on resonator networks at VSA workshop: https://youtu.be/T0mqBCpDqwk Papers: Frady, E.P., Sommer, F.T. (2019). Robust computation with rhythmic spike patterns. https://www.pnas.org/content/pnas/116/36/18050.full.pdf Frady, E.P., Kent, S., Sommer, F.T., Olshausen, B. (2020). Resonator networks 1, An Efficient Solution for Factoring High-Dimensional, Distributed Representations. https://redwood.berkeley.edu/wp-content/uploads/2020/08/resonator1.pdf Frady, E.P., Orchard, G., Florey, D., Imam, N., Liu, R., Mishra, J., Tse, J., Wild, A., Sommer, F.T. and Davies, M. (2020). Neuromorphic Nearest Neighbor Search Using Intel's Pohoiki Springs. https://dl.acm.org/doi/10.1145/3381755.3398695 Frady, E.P., Kleyko, D., Sommer, F.T. (2020). Variable Binding for Sparse Distributed Representations: Theory and Applications. https://arxiv.org/pdf/2009.06734.pdf Hyeryung Jang, Nicolas Skatchkovsky, and Osvaldo Simeone (2020). BISNN: Training spiking neural networks with binary weights via Bayesian learning. https://arxiv.org/pdf/2012.08300.pdf Yulia Sandamirskaya (2014). Dynamic neural fields as a step toward cognitive neuromorphic architectures. https://www.frontiersin.org/articles/10.3389/fnins.2013.00276/full Websites: VSA https://sites.google.com/ltu.se/vsaonline NEF https://www.nengo.ai/nengo/examples/advanced/nef-algorithm.html DNF |
Recording | Not yet availablehttps://intel.webex.com/recordingservice/sites/intel/recording/9a81723d9f324e3aa758784f451f896c/playback |
Link to Presentation | Not yet available |
...