Architectural Exploration of Hybrid Neural Decoders for Neuromorphic Implantable BMI
This work addresses the need for low-power, efficient decoding in neuromorphic implantable BMIs, representing an incremental improvement with specific gains in resource reduction.
The paper tackles the problem of high computational and memory demands in implantable brain-machine interfaces by introducing a tunable event filter and hybrid neural decoders, achieving up to R^2=0.73 decoding performance while reducing events processed by up to 554X and computations by up to 23X.
This work presents an efficient decoding pipeline for neuromorphic implantable brain-machine interfaces (Neu-iBMI), leveraging sparse neural event data from an event-based neural sensing scheme. We introduce a tunable event filter (EvFilter), which also functions as a spike detector (EvFilter-SPD), significantly reducing the number of events processed for decoding by 192X and 554X, respectively. The proposed pipeline achieves high decoding performance, up to R^2=0.73, with ANN- and SNN-based decoders, eliminating the need for signal recovery, spike detection, or sorting, commonly performed in conventional iBMI systems. The SNN-Decoder reduces computations and memory required by 5-23X compared to NN-, and LSTM-Decoders, while the ST-NN-Decoder delivers similar performance to an LSTM-Decoder requiring 2.5X fewer resources. This streamlined approach significantly reduces computational and memory demands, making it ideal for low-power, on-implant, or wearable iBMIs.