The BrainScaleS-2 accelerated neuromorphic system with hybrid plasticity
This work presents an incremental hardware architecture for neuromorphic computing, potentially benefiting researchers in AI and neuroscience by providing a platform for accelerated spiking neural network simulations.
The paper introduces the BrainScaleS-2 neuromorphic system, which tackles the challenge of brain-inspired computing by combining an analog accelerator for spiking neural networks with digital processing and event-routing, enabling accelerated emulation of bio-inspired neural primitives.
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.