Beck - Interview at Q101'a Twisted Christmas in Chicago (1998)
youtu.be/Cgcnn-bdVMA?...
#90s #alternative #alternativerock
youtu.be/Cgcnn-bdVMA?...
#90s #alternative #alternativerock
Beck Interview on MTV for Q101's Twisted Christmas in Chicago, December 1998
YouTube video by perfunctory-idols
youtu.be
December 24, 2024 at 7:45 PM
Beck - Interview at Q101'a Twisted Christmas in Chicago (1998)
youtu.be/Cgcnn-bdVMA?...
#90s #alternative #alternativerock
youtu.be/Cgcnn-bdVMA?...
#90s #alternative #alternativerock
in other news i got a graph transformer to resolve all its package/dependency errors, so i should be able to hook it up with the CGCNN frontend to do inference on crystals. will work on that tomorrow with setting up AccelWattch #fourthofjuly #america
July 4, 2025 at 5:54 AM
in other news i got a graph transformer to resolve all its package/dependency errors, so i should be able to hook it up with the CGCNN frontend to do inference on crystals. will work on that tomorrow with setting up AccelWattch #fourthofjuly #america
This review evaluates #CGCNN in #MaterialsInformatics, detailing architecture, limitations, and integration with #GenerativeModels, while outlining benchmarking and strategies to advance data‑driven #MaterialsDiscovery.
#OpenAccess in Nanotechnology Reviews: doi.org/10.1515/ntre...
#OpenAccess in Nanotechnology Reviews: doi.org/10.1515/ntre...
December 16, 2025 at 6:30 AM
This review evaluates #CGCNN in #MaterialsInformatics, detailing architecture, limitations, and integration with #GenerativeModels, while outlining benchmarking and strategies to advance data‑driven #MaterialsDiscovery.
#OpenAccess in Nanotechnology Reviews: doi.org/10.1515/ntre...
#OpenAccess in Nanotechnology Reviews: doi.org/10.1515/ntre...
SR-CGCNN: Shared Recurrent Convolution in Crystal Graph Neural Networks for Materials Property Prediction
https://arxiv.org/pdf/2605.01304
Satadeep Bhattacharjee.
https://arxiv.org/pdf/2605.01304
Satadeep Bhattacharjee.
https://arxiv.org/abs/2605.01304
arXiv abstract link
arxiv.org
May 5, 2026 at 4:31 AM
SR-CGCNN: Shared Recurrent Convolution in Crystal Graph Neural Networks for Materials Property Prediction
https://arxiv.org/pdf/2605.01304
Satadeep Bhattacharjee.
https://arxiv.org/pdf/2605.01304
Satadeep Bhattacharjee.
Satadeep Bhattacharjee: SR-CGCNN: Shared Recurrent Convolution in Crystal Graph Neural Networks for Materials Property Prediction https://arxiv.org/abs/2605.01304 https://arxiv.org/pdf/2605.01304 https://arxiv.org/html/2605.01304
May 5, 2026 at 6:52 AM
Satadeep Bhattacharjee: SR-CGCNN: Shared Recurrent Convolution in Crystal Graph Neural Networks for Materials Property Prediction https://arxiv.org/abs/2605.01304 https://arxiv.org/pdf/2605.01304 https://arxiv.org/html/2605.01304
predict \k{appa}L directly from crystallographic information files (CIFs). Unlike previous approaches, PINK enables rapid, batch predictions by extracting material properties such as bulk and shear modulus from CIFs using a well-trained CGCNN model. [4/7 of https://arxiv.org/abs/2503.17060v1]
March 24, 2025 at 6:09 AM
predict \k{appa}L directly from crystallographic information files (CIFs). Unlike previous approaches, PINK enables rapid, batch predictions by extracting material properties such as bulk and shear modulus from CIFs using a well-trained CGCNN model. [4/7 of https://arxiv.org/abs/2503.17060v1]
Search for Stable and Low-Energy Ce–Co–Cu Ternary Compounds Using Machine Learning
Search for Stable and Low-Energy Ce–Co–Cu Ternary Compounds Using Machine Learning
Cerium-based intermetallics have garnered significant research attention as potential new permanent magnets. In this study, we explore the compositional and structural landscape of Ce–Co–Cu ternary compounds using a machine learning (ML)-guided framework integrated with first-principles calculations. We employ a crystal graph convolutional neural network (CGCNN), which enables efficient screening for promising candidates, significantly accelerating the material discovery process. With this approach, we predict five stable compounds, Ce3Co3Cu, CeCoCu2, Ce12Co7Cu, Ce11Co9Cu, and Ce10Co11Cu4, with formation energies below the convex hull, along with hundreds of low-energy (possibly metastable) Ce–Co–Cu ternary compounds. First-principles calculations reveal that several structures are both energetically and dynamically stable. Notably, two Co-rich low-energy compounds, Ce4Co33Cu and Ce4Co31Cu3, are predicted to have high magnetizations.
pubs.acs.org
May 10, 2025 at 11:53 PM
Search for Stable and Low-Energy Ce–Co–Cu Ternary Compounds Using Machine Learning
Incorporating Mechanistic Insights into Structure–Property Modeling of Metal–Organic Frameworks for H2 and CH4 Adsorption: A CGCNN Approach http://dx.doi.org/10.1021/acs.iecr.4c03301
February 10, 2025 at 3:13 PM
Incorporating Mechanistic Insights into Structure–Property Modeling of Metal–Organic Frameworks for H2 and CH4 Adsorption: A CGCNN Approach http://dx.doi.org/10.1021/acs.iecr.4c03301
Chalcogenides and the Jarvis Dataset. The results show that the proposed model exhibits better zero shot performance than the individual plain vanilla CGCNN and SciBERT model. This enables researchers to deploy the model for specialized industrial [7/8 of https://arxiv.org/abs/2505.04634v1]
May 9, 2025 at 5:57 AM
Chalcogenides and the Jarvis Dataset. The results show that the proposed model exhibits better zero shot performance than the individual plain vanilla CGCNN and SciBERT model. This enables researchers to deploy the model for specialized industrial [7/8 of https://arxiv.org/abs/2505.04634v1]
of 40% compared to the vanilla CGCNN model and 68% compared to the SciBERT model for predicting the formation energy per atom. Importantly, we demonstrate the zero shot performance of the trained model on small curated datasets of Perovskites, [6/8 of https://arxiv.org/abs/2505.04634v1]
May 9, 2025 at 5:57 AM
of 40% compared to the vanilla CGCNN model and 68% compared to the SciBERT model for predicting the formation energy per atom. Importantly, we demonstrate the zero shot performance of the trained model on small curated datasets of Perovskites, [6/8 of https://arxiv.org/abs/2505.04634v1]
Project Dataset. We show that our proposed model shows an improvement compared to the vanilla CGCNN and SciBERT model for all four key properties: formation energy, band gap, energy above hull and fermi energy. Specifically, we observe an improvement [5/8 of https://arxiv.org/abs/2505.04634v1]
May 9, 2025 at 5:57 AM
Project Dataset. We show that our proposed model shows an improvement compared to the vanilla CGCNN and SciBERT model for all four key properties: formation energy, band gap, energy above hull and fermi energy. Specifically, we observe an improvement [5/8 of https://arxiv.org/abs/2505.04634v1]
multi-head attention mechanism for the combination of structure aware embedding from the Crystal Graph Convolution Network (CGCNN) and text embeddings from the SciBERT model. We train our model in an end-to-end framework using data from the Materials [4/8 of https://arxiv.org/abs/2505.04634v1]
May 9, 2025 at 5:57 AM
multi-head attention mechanism for the combination of structure aware embedding from the Crystal Graph Convolution Network (CGCNN) and text embeddings from the SciBERT model. We train our model in an end-to-end framework using data from the Materials [4/8 of https://arxiv.org/abs/2505.04634v1]
MatWheel framework, which train the material property prediction model using the synthetic data generated by the conditional generative model. We explore two scenarios: fully-supervised and semi-supervised learning. Using CGCNN for property prediction [2/5 of https://arxiv.org/abs/2504.09152v1]
April 15, 2025 at 6:11 AM
MatWheel framework, which train the material property prediction model using the synthetic data generated by the conditional generative model. We explore two scenarios: fully-supervised and semi-supervised learning. Using CGCNN for property prediction [2/5 of https://arxiv.org/abs/2504.09152v1]