Reward driven workflows for unsupervised explainable analysis of phases and ferroic variants from atomically resolved imaging data

• URL: http://arxiv.org/abs/2411.12612v1
• Date: Tue, 19 Nov 2024 16:18:20 GMT
• Title: Reward driven workflows for unsupervised explainable analysis of phases and ferroic variants from atomically resolved imaging data
• Authors: Kamyar Barakati, Yu Liu, Chris Nelson, Maxim A. Ziatdinov, Xiaohang Zhang, Ichiro Takeuchi, Sergei V. Kalinin,
• Abstract summary: We show that a reward-driven approach can be used to optimize key hyper parameters in unsupervised ML methods. This approach allows us to discover local descriptors that are best aligned with the specific physical behavior. We also extend the reward driven to disentangle structural factors of variation via variational autoencoder (VAE)
• Score: 14.907891992968361
• License:
• Abstract: Rapid progress in aberration corrected electron microscopy necessitates development of robust methods for the identification of phases, ferroic variants, and other pertinent aspects of materials structure from imaging data. While unsupervised methods for clustering and classification are widely used for these tasks, their performance can be sensitive to hyperparameter selection in the analysis workflow. In this study, we explore the effects of descriptors and hyperparameters on the capability of unsupervised ML methods to distill local structural information, exemplified by discovery of polarization and lattice distortion in Sm doped BiFeO3 (BFO) thin films. We demonstrate that a reward-driven approach can be used to optimize these key hyperparameters across the full workflow, where rewards were designed to reflect domain wall continuity and straightness, ensuring that the analysis aligns with the material's physical behavior. This approach allows us to discover local descriptors that are best aligned with the specific physical behavior, providing insight into the fundamental physics of materials. We further extend the reward driven workflows to disentangle structural factors of variation via optimized variational autoencoder (VAE). Finally, the importance of well-defined rewards was explored as a quantifiable measure of success of the workflow.

Related papers

• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture. We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• Unsupervised Reward-Driven Image Segmentation in Automated Scanning Transmission Electron Microscopy Experiments [0.22795086293129713]
  Automated experiments in scanning transmission electron microscopy (STEM) require rapid image segmentation to optimize data representation for human interpretation, decision-making, site-selective spectroscopies, and atomic manipulation. Here, we operationalize and benchmark a recently proposed reward-driven optimization workflow for on-the fly image analysis in STEM. This unsupervised approach is much more robust, as it does not rely on human labels and is fully explainable.
  arXiv  Detail & Related papers  (2024-09-19T04:51:13Z)
• Discovering deposition process regimes: leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis [0.1558630944877332]
  This work introduces a comprehensive approach to elucidate the deposition process regimes in Chemical Vapor Deposition (CVD) reactors. Our methodology relies on process outcomes, derived by a detailed CFD model, to identify clusters of "outcomes" corresponding to distinct process regimes. This phenomenon is experimentally validated through Arrhenius plot analysis, affirming the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-05-24T14:10:22Z)
• Physics-based reward driven image analysis in microscopy [5.581609660066545]
  We present a methodology based on the concept of a Reward Function to optimize image analysis dynamically. The Reward Function is engineered to closely align with the experimental objectives and broader context. We extend the reward function approach towards the identification of partially-disordered regions, creating a physics-driven reward function and action space of high-dimensional clustering.
  arXiv  Detail & Related papers  (2024-04-22T12:55:04Z)
• Physics Inspired Hybrid Attention for SAR Target Recognition [61.01086031364307]
  We propose a physics inspired hybrid attention (PIHA) mechanism and the once-for-all (OFA) evaluation protocol to address the issues. PIHA leverages the high-level semantics of physical information to activate and guide the feature group aware of local semantics of target. Our method outperforms other state-of-the-art approaches in 12 test scenarios with same ASC parameters.
  arXiv  Detail & Related papers  (2023-09-27T14:39:41Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)
• Combining Variational Autoencoders and Physical Bias for Improved Microscopy Data Analysis [0.0]
  We present a physics augmented machine learning method which disentangles factors of variability within the data. Our method is applied to various materials, including NiO-LSMO, BiFeO3, and graphene. The results demonstrate the effectiveness of our approach in extracting meaningful information from large volumes of imaging data.
  arXiv  Detail & Related papers  (2023-02-08T17:35:38Z)
• Designing Robust Transformers using Robust Kernel Density Estimation [47.494628752936165]
  We introduce a series of self-attention mechanisms that can be incorporated into different Transformer architectures. We then perform extensive empirical studies on language modeling and image classification tasks.
  arXiv  Detail & Related papers  (2022-10-11T21:39:52Z)
• Pre-training via Denoising for Molecular Property Prediction [53.409242538744444]
  We describe a pre-training technique that utilizes large datasets of 3D molecular structures at equilibrium. Inspired by recent advances in noise regularization, our pre-training objective is based on denoising.
  arXiv  Detail & Related papers  (2022-05-31T22:28:34Z)
• Information-Theoretic Odometry Learning [83.36195426897768]
  We propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language.
  arXiv  Detail & Related papers  (2022-03-11T02:37:35Z)
• A physics-informed operator regression framework for extracting data-driven continuum models [0.0]
  We present a framework for discovering continuum models from high fidelity molecular simulation data. Our approach applies a neural network parameterization of governing physics in modal space. We demonstrate the effectiveness of our framework for a variety of physics, including local and nonlocal diffusion processes and single and multiphase flows.
  arXiv  Detail & Related papers  (2020-09-25T01:13:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.