What is neuromorphic computing?
Neuromorphic computing is a technique that mimics brain functionality. Therefore to be neuromorphic engineer, one should understand enough biology, physics, electronics and computer science. Neuromorphic computing, tries to emulate how biological neurons and synapses work in order to process a data.
Neuromorphic computing as it mimics the brain, therefore it essentially based on Artifical Neural Network(ANN). ANN model are widely searched on Von Neumann architecture based CPUs and Spiking Neural network is one of the subject of ANN models.
Spiking Neural Networks
As other ANN models on CPUs and GPUs are well documented, SNNs are poorly researched about and therefore cabalities of SNNs should be well understood as it was the case several years ago. But the gap between other ANN models and SNN is decreasing, the key difference about SNN is that we should have an processing unit different than von neumann architecture based computers.
Sites to watch
- https://open-neuromorphic.org/
References
[1] Kudithipudi, D., Schuman, C., Vineyard, C.M. et al. Neuromorphic computing at scale. Nature 637, 801–812 (2025). https://doi.org/10.1038/s41586-024-08253-8
[2] Mayr, C., Hoeppner, S., & Furber, S. (2019). SpiNNaker 2: A 10 million core processor system for brain simulation and machine learning-keynote presentation. In Communicating Process Architectures 2017 & 2018 (pp. 277-280). IOS Press.
[3] Davies, M., Srinivasa, N., Lin, T. H., Chinya, G., Cao, Y., Choday, S. H., … & Wang, H. (2018). Loihi: A neuromorphic manycore processor with on-chip learning. Ieee Micro, 38(1), 82-99.