Saved in:
Bibliographic Details
Main Authors: Ge, Ningling, Dai, Sicheng, Zhu, Yu, Yu, Shan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.17606
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917098129719296
author Ge, Ningling
Dai, Sicheng
Zhu, Yu
Yu, Shan
author_facet Ge, Ningling
Dai, Sicheng
Zhu, Yu
Yu, Shan
contents Understanding brain function represents a fundamental goal in neuroscience, with critical implications for therapeutic interventions and neural engineering applications. Computational modeling provides a quantitative framework for accelerating this understanding, but faces a fundamental trade-off between computational efficiency and high-fidelity modeling. To address this limitation, we introduce a novel Energy-based Autoregressive Generation (EAG) framework that employs an energy-based transformer learning temporal dynamics in latent space through strictly proper scoring rules, enabling efficient generation with realistic population and single-neuron spiking statistics. Evaluation on synthetic Lorenz datasets and two Neural Latents Benchmark datasets (MC_Maze and Area2_bump) demonstrates that EAG achieves state-of-the-art generation quality with substantial computational efficiency improvements, particularly over diffusion-based methods. Beyond optimal performance, conditional generation applications show two capabilities: generalizing to unseen behavioral contexts and improving motor brain-computer interface decoding accuracy using synthetic neural data. These results demonstrate the effectiveness of energy-based modeling for neural population dynamics with applications in neuroscience research and neural engineering. Code is available at https://github.com/NinglingGe/Energy-based-Autoregressive-Generation-for-Neural-Population-Dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17606
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Energy-based Autoregressive Generation for Neural Population Dynamics
Ge, Ningling
Dai, Sicheng
Zhu, Yu
Yu, Shan
Machine Learning
Artificial Intelligence
Understanding brain function represents a fundamental goal in neuroscience, with critical implications for therapeutic interventions and neural engineering applications. Computational modeling provides a quantitative framework for accelerating this understanding, but faces a fundamental trade-off between computational efficiency and high-fidelity modeling. To address this limitation, we introduce a novel Energy-based Autoregressive Generation (EAG) framework that employs an energy-based transformer learning temporal dynamics in latent space through strictly proper scoring rules, enabling efficient generation with realistic population and single-neuron spiking statistics. Evaluation on synthetic Lorenz datasets and two Neural Latents Benchmark datasets (MC_Maze and Area2_bump) demonstrates that EAG achieves state-of-the-art generation quality with substantial computational efficiency improvements, particularly over diffusion-based methods. Beyond optimal performance, conditional generation applications show two capabilities: generalizing to unseen behavioral contexts and improving motor brain-computer interface decoding accuracy using synthetic neural data. These results demonstrate the effectiveness of energy-based modeling for neural population dynamics with applications in neuroscience research and neural engineering. Code is available at https://github.com/NinglingGe/Energy-based-Autoregressive-Generation-for-Neural-Population-Dynamics.
title Energy-based Autoregressive Generation for Neural Population Dynamics
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.17606