DBNN: Neural Spike Classification Using a Deep Binarized Neural Network

2026-07-06

AI Summary

This work proposes a hardware-oriented deep binary neural network (DBNN) for real-time neural spike classification to reduce telemetry bandwidth and power consumption in implantable brain–computer interfaces. The architecture employs two 256-neuron binary hidden layers and a fixed-point output layer, enabling multiplier-free inference through sign-controlled accumulation and bitwise operations while maintaining accuracy and efficiency with 16-sample inputs. As the first study to apply DBNNs to real-time spike sorting, it achieves a median accuracy of 98.7% on both synthetic and in vivo datasets. The FPGA prototype exhibits a latency of only 0.01 ms, and the ASIC implementation in FreePDK45 occupies 0.014 mm² with a power consumption of merely 122 nW at 20 kHz.

Abstract

Implantable brain-computer interfaces require on-node spike sorting to reduce telemetry bandwidth and power while maintaining reliable neural decoding. This paper presents a hardware-oriented deep binarized neural network (DBNN) spike-sorting system with two binarized hidden layers with 256 neurons and a fixed-point output layer to enable multiplier-free inference dominated by sign-controlled accumulation and bit-wise logic. The proposed classifier operates on compact 16-sample spike waveforms to reduce the implementation cost (16-256-256-3) and achieves a median classification accuracy of 98.7% on both synthetic and in-vivo datasets. An FPGA prototype on a Cyclone V device operates at 50 MHz and requires 528 cycles per spike, corresponding to a 0.01 ms compute latency, while consuming 828 ALMs and 1023 registers with zero DSP blocks. For ASIC feasibility, the DBNN is implemented using FreePDK45-based flow; synthesis in Synopsys Design Compiler indicates an estimated silicon area of 0.014 mm2 and an operating power of 122 nW at 20 kHz under a 1.1 V supply. These results demonstrate that the proposed DBNN spike sorter offers a favorable trade-off between accuracy and implementation cost, supporting low-power, implantable neural interfaces. Overall, the proposed DBNN spike sorter achieves high accuracy (98.7%) with extremely low hardware cost (0.014 mm2, 122 nW at 20 kHz) and multiplier-free operation, making it suitable for low-power, implantable neural interfaces. This paper introduces the first DBNN designed for real-time neural spike sorting, striking an excellent balance between input data size and network complexity.

Problem

• spike sorting
• brain-computer interface
• low-power
• implantable neural interface
• neural decoding

Innovation

• Deep Binarized Neural Network
• Spike Sorting
• Multiplier-free Inference
• Low-power ASIC
• Implantable Brain-Computer Interface