mlsanityData to 7 Oct 2026

Neural Network Modeling of Microstructure Complexity Using Digital Libraries

arXiv 2501.18189 ↗First posted 30 Jan 2025cs.LG cond-mat.mtrl-sci cs.CEcited by 0

Not on the map. Why?

Abstract (arXiv)

Microstructure evolution in matter is often modeled numerically using field or level-set solvers, mirroring the dual representation of spatiotemporal complexity in terms of pixel or voxel data, and geometrical forms in vector graphics. Motivated by this analog, as well as the structural and event-driven nature of artificial and spiking neural networks, respectively, we evaluate their performance in learning and predicting fatigue crack growth and Turing pattern development. Predictions are made based on digital libraries constructed from computer simulations, which can be replaced by experimental data to lift the mathematical overconstraints of physics. Our assessment suggests that the leaky integrate-and-fire neuron model offers superior predictive accuracy with fewer parameters and less memory usage, alleviating the accuracy-cost tradeoff in contrast to the common practices in computer vision tasks. Examination of network architectures shows that these benefits arise from its reduced weight range and sparser connections. The study highlights the capability of event-driven models in tackling problems with evolutionary bulk-phase and interface behaviors using the digital library approach.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 59 references that are in the map. First posted on arXiv 30 Jan 2025.

Builds on

21 of 59 references.

References · 21

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  4. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
  5. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  6. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  7. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  8. 2015Unsupervised Learning of Video Representations using LSTMscited by 434
  9. 2018Deep Learning in Spiking Neural Networkscited by 258
  10. 2022SimVP: Simpler yet Better Video Predictioncited by 181
  11. 2024The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learningcited by 134
  12. 2018PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learningcited by 122
9 more
  1. 2023In-Context Operator Learning with Data Prompts for Differential Equation Problemscited by 98
  2. 2020A Probabilistic Graphical Model Foundation for Enabling Predictive Digital Twins at Scalecited by 58
  3. 2023OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learningcited by 53
  4. 2020Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differencescited by 39
  5. 2023TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modellingcited by 21
  6. 2024Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulationcited by 12
  7. 2022Spiking neural networks for nonlinear regressioncited by 10
  8. 2022Spiking Neural Operators for Scientific Machine Learningcited by 8
  9. 2024PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplinescited by 6

Built on by

Not cited yet.