深度压缩自动编码器在大规模神经记录中的应用
Deep Compressive Autoencoder for Action Potential Compression in Large-Scale Neural Recording
摘要:
理解大脑计算背后的协调活动需要大规模的,同时记录分布式神经元结构在细胞水平的分辨率。设计高带宽、高精度、大规模神经接口的一个主要障碍在于记录器芯片产生的强大数据流,这些数据流需要在线传输到远程计算机。数据率可能需要记录器芯片上的数百到数千个I/O焊盘,并且仅用于数据流的功耗就在瓦特量级。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率。所提出的模型是建立在一个深度压缩自动编码器(CAE)与离散潜在嵌入。编码器配备有残差变换,以从尖峰信号中提取代表性特征,这些特征被映射到潜在嵌入空间并通过矢量量化(VQ)进行更新。解码器网络从量化的潜在嵌入重构尖峰波形。实验结果表明,该模型始终优于传统的方法,实现更高的压缩比(20- 500倍)和更好的或相当的重建精度。测试结果还表明,CAE是强大的对各种各样的缺陷,如波形变化和尖峰错位,并有微小的影响尖峰排序精度。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记录通道,而不会产生过多的功耗/散热。该模型可以降低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。该工作的代码已在https://github.com/tong-wu-umn/spike-compression-autoencoder上提供
英文摘要:
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
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。