Machine learning and experiments: A synergy for the development of functional materials

Zheng, Bowen; Jin, Zeqing; Hu, Grace; Gu, Jimin; Yu, Shao-Yi; Lee, Jehee; Gu, Grace X.

doi:10.1557/s43577-023-00492-w

Cited by 8 publications

(1 citation statement)

References 136 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The collection and usage of data have received rigorous Institutional Review Board review. The appendix and source code are presented in (Zheng, Yu, and Zheng 2023).…”

Section: Methodsmentioning

confidence: 99%

Sparse Maximum Margin Learning from Multimodal Human Behavioral Patterns

Zheng

2023

AAAI

View full text Add to dashboard Cite

We propose a multimodal data fusion framework to systematically analyze human behavioral data from specialized domains that are inherently dynamic, sparse, and heterogeneous. We develop a two-tier architecture of probabilistic mixtures, where the lower tier leverages parametric distributions from the exponential family to extract significant behavioral patterns from each data modality. These patterns are then organized into a dynamic latent state space at the higher tier to fuse patterns from different modalities. In addition, our framework jointly performs pattern discovery and maximum-margin learning for downstream classification tasks by using a group-wise sparse prior that regularizes the coefficients of the maximum-margin classifier. Therefore, the discovered patterns are highly interpretable and discriminative to support downstream classification tasks. Experiments on real-world behavioral data from medical and psychological domains demonstrate that our framework discovers meaningful multimodal behavioral patterns with improved interpretability and prediction performance.

show abstract

“…The collection and usage of data have received rigorous Institutional Review Board review. The appendix and source code are presented in (Zheng, Yu, and Zheng 2023).…”

Section: Methodsmentioning

confidence: 99%

Sparse Maximum Margin Learning from Multimodal Human Behavioral Patterns

Zheng

2023

AAAI

View full text Add to dashboard Cite

show abstract

Investigating Static and Dynamic Behaviors in 3D Chiral Mechanical Metamaterials by Disentangled Generative Models

Park,

Noh,

Shin

et al. 2024

Adv Funct Materials

View full text Add to dashboard Cite

Chiral mechanical metamaterials with engineered asymmetric structures have garnered significant interest owing to their potential for manipulating mechanical waves and unconventional mechanical properties. Although several design methodologies have made significant strides in the design and discovery of chiral mechanical metamaterials, 3D designs that incorporate multiple mechanical characteristics remain largely unexplored and the static and dynamic properties of these structures have not received sufficient attention. Here, an innovative approach is introduced for the inverse design of 3D chiral mechanical metamaterials with desired static and dynamic properties, leveraging streamlined shapes to enable a versatile design. By employing conditional generative adversarial networks (c‐GANs), the desired mechanical properties are targeted by focusing on both wave attenuation and stress distribution under compression and shear loading. 3D chiral mechanical metamaterials with additive manufacturing are fabricated to demonstrate the performance of the proposed c‐GAN. Experimental investigations show that the generated structures exhibited a wide range of wave attenuation properties, low stress concentrations, and a variety of stress‐strain curve profiles including nonlinear stiffness, demonstrating their effectiveness in achieving the desired mechanical characteristics. This research offers significant advancements in the on‐demand design capabilities of metamaterials and their applications.

show abstract

Deep learning based automated fracture identification in material characterization experiments

Karathanasopoulos,

Hadjidoukas

2024

Advanced Engineering Informatics

View full text Add to dashboard Cite

Machine learning and experiments: A synergy for the development of functional materials

Cited by 8 publications

References 136 publications

Sparse Maximum Margin Learning from Multimodal Human Behavioral Patterns

Sparse Maximum Margin Learning from Multimodal Human Behavioral Patterns

Investigating Static and Dynamic Behaviors in 3D Chiral Mechanical Metamaterials by Disentangled Generative Models

Deep learning based automated fracture identification in material characterization experiments

Contact Info

Product

Resources

About