# FPGA Deployment of LFADS for Real-time Neuroscience Experiments

arXiv: https://arxiv.org/abs/2402.04274 · HTML: https://mlsanity.com/paper/2402.04274/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 10 of 10)

- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Fast inference of deep neural networks in FPGAs for particle physics](https://mlsanity.com/paper/1804.06913/) (2018)
- [Fast convolutional neural networks on FPGAs with hls4ml](https://mlsanity.com/paper/2101.05108/) (2021)
- [LFADS - Latent Factor Analysis via Dynamical Systems](https://mlsanity.com/paper/1608.06315/) (2016)
- [A Comprehensive Review of Deep Learning Applications in Hydrology and Water Resources](https://mlsanity.com/paper/2007.12269/) (2020)
- [Artificial neural networks for neuroscientists: A primer](https://mlsanity.com/paper/2006.01001/) (2020)
- [Targeted Neural Dynamical Modeling](https://mlsanity.com/paper/2110.14853/) (2021)
- [A Survey of FPGA-Based Neural Network Accelerator](https://mlsanity.com/paper/1712.08934/) (2017)
- [AutoEncoder by Forest](https://mlsanity.com/paper/1709.09018/) (2017)

## Abstract (arXiv)

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 μs for processing the data in a single trial on a Xilinx U55C.