paper-with-me

홈 › Papers

Neurons for Neutrons: A Transformer Model for Computation Load Estimation on Domain-Decomposed Neutron Transport Problems

2024-11-05 · Alexander Mote, Todd Palmer, Lizhong Chen

Domain decomposition is a technique used to reduce memory overhead on large neutron transport problems. Currently, the optimal load-balanced processor allocation for these domains is typically determined through small-scale simulations of the problem, which can be time-consuming for researchers and must be repeated anytime a problem input is changed. We propose a Transformer model with a unique 3D input embedding, and input representations designed for domain-decomposed neutron transport problems, which can predict the subdomain computation loads generated by small-scale simulations. We demonstrate that such a model trained on domain-decomposed Small Modular Reactor (SMR) simulations achieves 98.2% accuracy while being able to skip the small-scale simulation step entirely. Tests of the model's robustness on variant fuel assemblies, other problem geometries, and changes in simulation parameters are also discussed.

📄 PDF Abstract BibTeX arXiv:2411.03389

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Attention 설명 없음
Multi-Head Attention 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams

2023-12-05 · Chaoyi Chen, Dechao Gao, Yanfeng Zhang, Qiange Wang 외

Existing Graph Neural Network (GNN) training frameworks have been designed to help developers easily create performant GNN implementations. However, most existing GNN frameworks assume that the input graphs are static, b…

Graph Neural Network

Irradiation Tests for Commercial Off-the Shelf Components with Atmospheric-like Neutrons and Heavy-Ions

2023-11-29 · Paolo Branchini, Andrea Fabbri, Sacha Cormenier, Marco Bernardini 외

This paper presents the results of the irradiation, performed with atmospheric-like neutrons and heavy-ions, of Commercial Off-the Shelf Components (COTS), which can be used in space missions. In such cases, it is crucia…

LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons

2025-11-02 · Shashank Nag, Alan T. L. Bacellar, Zachary Susskind, Anshul Jha 외 arxiv

Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on FPGAs -- a field that has seen a recent…

From Neurons to Neutrons: A Case Study in Interpretability

2024-05-27 · Ouail Kitouni, Niklas Nolte, Víctor Samuel Pérez-Díaz, Sokratis Trifinopoulos 외

Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a…

One-Block Transformer (1BT) for EEG-Based Cognitive Workload Assessment

2026-04-21 · Stefanos Gkikas, Christian Arzate Cruz, Thomas Kassiotis, Giorgos Giannakakis 외 arxiv

Accurate and continuous estimation of cognitive workload is fundamental to creating adaptive human-machine systems. However, designing architectures that balance representational capacity with computational efficiency ha…

Computational EfficiencyTemporal Sequences