Spiking Linear Dynamical Systems on Neuromorphic Hardware for Low-Power Brain-Machine Interfaces
This work enables low-power brain-machine interfaces and other applications like navigation or robotics by leveraging neuromorphic hardware for efficient computation.
The authors developed methods to perform precise linear computations using spiking neural networks on neuromorphic hardware, specifically mapping a linear dynamical system onto IBM's TrueNorth chip, and demonstrated its utility by implementing a neuromorphic Kalman filter for offline decoding of human vocal pitch from neural data.
Neuromorphic architectures achieve low-power operation by using many simple spiking neurons in lieu of traditional hardware. Here, we develop methods for precise linear computations in spiking neural networks and use these methods to map the evolution of a linear dynamical system (LDS) onto an existing neuromorphic chip: IBM's TrueNorth. We analytically characterize, and numerically validate, the discrepancy between the spiking LDS state sequence and that of its non-spiking counterpart. These analytical results shed light on the multiway tradeoff between time, space, energy, and accuracy in neuromorphic computation. To demonstrate the utility of our work, we implemented a neuromorphic Kalman filter (KF) and used it for offline decoding of human vocal pitch from neural data. The neuromorphic KF could be used for low-power filtering in domains beyond neuroscience, such as navigation or robotics.