Results 261 to 270 of about 1,043,448 (307)

Going Beyond Persistent Homology Using Persistent Homology

Souza Amauri, Garg Vikas
openaire   +1 more source

Adaptive and Biochemical Responses of Dictyosphaerium sp. AM‐2024a to Environmental Conditions and Microplastic Interactions: Synergy of Biofuel Production With Pollution Mitigation

Biotechnology and Applied Biochemistry, EarlyView.
ABSTRACT This study investigates the physiological and biochemical responses of a newly isolated microalgal strain, Dictyosphaerium sp. AM‐2024a, identified through 18S rDNA sequencing, under varying environmental conditions and microplastic (MP) interactions.
Khushboo Iqbal, Arti Mishra, Smitha Mony Sreedharan   +2 more
wiley   +1 more source

Going beyond persistent homology using persistent homology

Neural Information Processing Systems, 2023
Representational limits of message-passing graph neural networks (MP-GNNs), e.g., in terms of the Weisfeiler-Leman (WL) test for isomorphism, are well understood.
Johanna Immonen, Amauri H. Souza, Vikas Garg   +2 more
semanticscholar   +4 more sources

Some of the next articles are maybe not open access.

Related searches:

Persistent Intersection Homology

Foundations of Computational Mathematics, 2010
Persistent homology uses a filtration on a topological space to define birth and death of a homology class. The \(r\)-dimensional classes that are born at stage \(i\) and die at stage \(j\) form the pair group \(P^{i,j}_r\), a vector space over the field with 2 elements, of the filtered space.
Bendich, Paul, Harer, John
openaire   +1 more source

Adversarially Trained Persistent Homology Based Graph Convolutional Network for Disease Identification Using Brain Connectivity

IEEE Transactions on Medical Imaging, 2023
Brain disease propagation is associated with characteristic alterations in the structural and functional connectivity networks of the brain. To identify disease-specific network representations, graph convolutional networks (GCNs) have been used because ...
Chenyuan Bian, N. Xia, A. Xie, S. Cong, Q. Dong   +4 more
semanticscholar   +1 more source

PHG-Net: Persistent Homology Guided Medical Image Classification*

IEEE Workshop/Winter Conference on Applications of Computer Vision, 2023
Modern deep neural networks have achieved great successes in medical image analysis. However, the features captured by convolutional neural networks (CNNs) or Transformers tend to be optimized for pixel intensities and neglect key anatomical structures ...
Yao Peng, Hongxiao Wang, Milan Sonka, D. Z. Chen   +3 more
semanticscholar   +1 more source

Improving Self-supervised Molecular Representation Learning using Persistent Homology

Neural Information Processing Systems, 2023
Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and the hence ...
Yuankai Luo, Lei Shi, Veronika Thost
semanticscholar   +1 more source

Topological data analysis and topological deep learning beyond persistent homology: a review

Artificial Intelligence Review
Topological data analysis (TDA) is a rapidly evolving field in applied mathematics and data science that leverages tools from topology to uncover robust, shape-driven, and explainable insights in complex datasets.
Zhe Su, Xiang Liu, Layal Bou Hamdan, Vasileios Maroulas, Jie Wu, Gunnar E. Carlsson, Guo-Wei Wei   +6 more
semanticscholar   +1 more source

Join Persistent Homology (JPH)-Based Machine Learning for Metalloprotein-Ligand Binding Affinity Prediction

Journal of Chemical Information and Modeling
With the crucial role of metalloproteins in respiration, oxidative stress protection, photosynthesis, and drug metabolism, the design and discovery of drugs that can target metalloproteins are extremely important.
Yaxing Wang, Xiang Liu, Yipeng Zhang, Xiangjun Wang, Kelin Xia   +4 more
semanticscholar   +1 more source

Differentiability and Optimization of Multiparameter Persistent Homology

International Conference on Machine Learning
Real-valued functions on geometric data -- such as node attributes on a graph -- can be optimized using descriptors from persistent homology, allowing the user to incorporate topological terms in the loss function.
Luis Scoccola, S. Setlur, David Loiseaux, Mathieu Carrière, Steve Oudot   +4 more
semanticscholar   +1 more source