.png){kind=icon}
返回
Accelerating graph-based tracking tasks with symbolic regression
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/ad8f12.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The reconstruction of particle tracks from hits in tracking detectors is a computationally intensive task due to the large combinatorics of detector signals. Recent efforts have proven that ML techniques can be successfully applied to the tracking problem, extending and improving the conventional methods based on feature engineering. However, complex models can be challenging to implement on heterogeneous trigger systems, integrating architectures such as field programmable gate arrays (FPGAs). Deploying the network on an FPGA is feasible but challenging and limited by its resources. An efficient alternative can employ symbolic regression (SR). We propose a novel approach that uses SR to replace a graph-based neural network. Substituting each network block with a symbolic function preserves the graph structure of the data and enables message passing. The technique is perfectly suitable for heterogeneous hardware, as it can be implemented more easily on FPGAs and grants faster execution times on CPU with respect to conventional methods. While the tracking problem is the target for this work, it also provides a proof-of-principle for the method that can be applied to many use cases.
Keyword:
graph neural networks
object condensation
symbolic regression
期刊
M
IF:
4.6
论文数:
1.1K
被引数:
3.4K
机构
引用论文
分享收藏Comparison of Histones Obtained from Mammary Gland at Different Stages of Development and Lactation不同发育和泌乳阶段乳腺组织中组蛋白的比较
OAAI
OAAI分享收藏INNOVATION IN EXTRACTION TECHNOLOGY FOR IMPROVED VIRGIN OLIVE OIL QUALITY AND BY-PRODUCT VALORISATION改进初榨橄榄油质量和副产物增值的提取技术创新
PREAI
分享收藏The role of power versus energy in courtship: what is the ‘energetic cost’ of a courtship display?
PREAI
分享收藏SciPy 1.0: fundamental algorithms for scientific computing in PythonSciPy 1.0: Python中科学计算的基本算法.png)
NATURE METHODSOAAI
NATURE METHODSIF32.1
OAAI分享收藏
查看更多内容