FPGA Deployment of LFADS for Real-time Neuroscience Experiments
This enables real-time analysis of neural recordings for neuroscientists, though it is incremental as it focuses on hardware optimization of an existing method.
The authors tackled the need for low-latency inference in neuroscience by deploying the LFADS algorithm on an FPGA, achieving an inference latency of 41.97 μs for single-trial neural data processing.
Large-scale recordings of neural activity are providing new opportunities to study neural population dynamics. A powerful method for analyzing such high-dimensional measurements is to deploy an algorithm to learn the low-dimensional latent dynamics. LFADS (Latent Factor Analysis via Dynamical Systems) is a deep learning method for inferring latent dynamics from high-dimensional neural spiking data recorded simultaneously in single trials. This method has shown a remarkable performance in modeling complex brain signals with an average inference latency in milliseconds. As our capacity of simultaneously recording many neurons is increasing exponentially, it is becoming crucial to build capacity for deploying low-latency inference of the computing algorithms. To improve the real-time processing ability of LFADS, we introduce an efficient implementation of the LFADS models onto Field Programmable Gate Arrays (FPGA). Our implementation shows an inference latency of 41.97 $μ$s for processing the data in a single trial on a Xilinx U55C.