Emulating Dendritic Computing Paradigms on Analog Neuromorphic Hardware

Kaiser, Jakob; Billaudelle, Sebastian; Müller, Eric; Tetzlaff, Christian; Schemmel, Johannes; Schmitt, Sebastian

doi:10.1016/j.neuroscience.2021.08.013

Cited by 29 publications

(25 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system design meets our expectations concerning flexibility and configurability of the analog components and has proven to be a versatile platform for implementing a wide array of tasks across several domains. The modularity of the architecture, in particular, the neuron circuits, allows for the evaluation of the implemented neuron models on a wide range of parameters as seen in Section 3.1 and even accelerated emulation of multi-compartment neurons (Kaiser et al, 2021). The hybrid approach of combining the analog core with flexible digital control and plasticity architecture has enabled many of the experiments reported here.…”

Section: Discussionmentioning

confidence: 99%

“…The modularity of the architecture, in particular, the neuron circuits, allows for the evaluation of the implemented neuron models on a wide range of parameters as seen in Section 3.1 and even accelerated emulation of multi-compartment neurons (Kaiser et al, 2021 ). The hybrid approach of combining the analog core with flexible digital control and plasticity architecture has enabled many of the experiments reported here.…”

Section: Discussionmentioning

confidence: 99%

“…On the other hand, the neuronal dynamics can also be extended. Using additional resistors and switches between the neuron circuits, larger cells with an increased synaptic fan-in as well as intricately structured neurons can be formed (Aamir et al, 2018a ; Kaiser et al, 2021 ).…”

Section: The Brainscales-2 Systemmentioning

confidence: 99%

“…To further demonstrate the high configurability of the system at hand we want to show how multi-compartmental models can be emulated. As mentioned in Section 2.2, BrainScales-2 offers the possibility to connect several neuron circuits and therefore allows to implement various compartmental neuron models (Kaiser et al, 2021 ).…”

Section: Applications Of the Brainscales-2 Systemmentioning

confidence: 99%

“…The traces show the membrane potential in compartment 0 . Figure adapted from Kaiser et al ( 2021 ).…”

Section: Applications Of the Brainscales-2 Systemmentioning

confidence: 99%

See 4 more Smart Citations

The BrainScaleS-2 Accelerated Neuromorphic System With Hybrid Plasticity

et al. 2022

Self Cite

View full text Add to dashboard Cite

Since the beginning of information processing by electronic components, the nervous system has served as a metaphor for the organization of computational primitives. Brain-inspired computing today encompasses a class of approaches ranging from using novel nano-devices for computation to research into large-scale neuromorphic architectures, such as TrueNorth, SpiNNaker, BrainScaleS, Tianjic, and Loihi. While implementation details differ, spiking neural networks—sometimes referred to as the third generation of neural networks—are the common abstraction used to model computation with such systems. Here we describe the second generation of the BrainScaleS neuromorphic architecture, emphasizing applications enabled by this architecture. It combines a custom analog accelerator core supporting the accelerated physical emulation of bio-inspired spiking neural network primitives with a tightly coupled digital processor and a digital event-routing network.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%