Abstract
Understanding the coordinated activity underlying brain computations requires large-scale, simultaneous recordings from distributed neuronal structures at a cellular-level resolution. One major hurdle to design high-bandwidth, high-precision, large-scale neural interfaces lies in the formidable data streams that are generated by the recorder chip and need to be online transferred to a remote computer. The data rates can require hundreds to thousands of I/O pads on the recorder chip and power consumption on the order of Watts for data streaming alone. We developed a deep learning-based compression model to reduce the data rate of multichannel action potentials. The proposed model is built upon a deep compressive autoencoder (CAE) with discrete latent embeddings. The encoder is equipped with residual transformations to extract representative features from spikes, which are mapped into the latent embedding space and updated via vector quantization (VQ). The decoder network reconstructs spike waveforms from the quantized latent embeddings. Experimental results show that the proposed model consistently outperforms conventional methods by achieving much higher compression ratios (20-500x) and better or comparable reconstruction accuracies. Testing results also indicate that CAE is robust against a diverse range of imperfections, such as waveform variation and spike misalignment, and has minor influence on spike sorting accuracy. Furthermore, we have estimated the hardware cost and real-time performance of CAE and shown that it could support thousands of recording channels simultaneously without excessive power/heat dissipation. The proposed model can reduce the required data transmission bandwidth in large-scale recording experiments and maintain good signal qualities. The code of this work has been made available at https://github.com/tong-wu-umn/spike-compression-autoencoder.
Abstract (translated)
理解大脑计算的协调活动需要在细胞水平分辨率下从分布式神经元结构进行大规模同步记录。设计高带宽,高精度,大规模神经接口的一个主要障碍在于由记录器芯片生成的强大数据流,需要在线传输到远程计算机。数据速率可能需要记录器芯片上数百到数千个I / O焊盘,单独数据流的功耗大约为瓦特。我们开发了一种基于深度学习的压缩模型,以降低多通道动作电位的数据速率。所提出的模型建立在具有离散潜在嵌入的深度压缩自动编码器(CAE)的基础上。编码器配备有残差变换以从尖峰中提取代表性特征,尖峰被映射到潜在嵌入空间并通过矢量量化(VQ)更新。解码器网络从量化的潜在嵌入中重建尖峰波形。实验结果表明,所提出的模型通过实现更高的压缩比(20-500x)和更好或相当的重建精度,始终优于传统方法。测试结果还表明,CAE可以抵抗各种各样的缺陷,例如波形变化和尖峰未对准,并且对尖峰分选精度影响很小。此外,我们估计了CAE的硬件成本和实时性能,并表明它可以同时支持数千个录制通道,而不会产生过多的功率/散热。所提出的模型可以减少大规模记录实验中所需的数据传输带宽并保持良好的信号质量。这项工作的代码已在https://github.com/tong-wu-umn/spike-compression-autoencoder上提供。
URL
https://arxiv.org/abs/1809.05522