FPGA Deployment of LFADS for Real-time Neuroscience Experiments
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917583936028672 |
|---|---|
| author | Liu, Xiaohan Chen, ChiJui Huang, YanLun Yang, LingChi Khoda, Elham E Chen, Yihui Hauck, Scott Hsu, Shih-Chieh Lai, Bo-Cheng |
| author_facet | Liu, Xiaohan Chen, ChiJui Huang, YanLun Yang, LingChi Khoda, Elham E Chen, Yihui Hauck, Scott Hsu, Shih-Chieh Lai, Bo-Cheng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_04274 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FPGA Deployment of LFADS for Real-time Neuroscience Experiments Liu, Xiaohan Chen, ChiJui Huang, YanLun Yang, LingChi Khoda, Elham E Chen, Yihui Hauck, Scott Hsu, Shih-Chieh Lai, Bo-Cheng Neurons and Cognition Machine Learning Neural and Evolutionary Computing 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. |
| title | FPGA Deployment of LFADS for Real-time Neuroscience Experiments |
| topic | Neurons and Cognition Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2402.04274 |