paper-with-me

Papers

Persistent Topological Structures and Cohomological Flows as a Mathematical Framework for Brain-Inspired Representation Learning

2025-12-09 · Preksha Girish, Rachana Mysore, Mahanthesha U, Shrey Kumar, Shipra Prashant arxiv

This paper presents a mathematically rigorous framework for brain-inspired representation learning founded on the interplay between persistent topological structures and cohomological flows. Neural computation is reformulated as the evolution of cochain maps over dynamic simplicial complexes, enabling representations that capture invariants across temporal, spatial, and functional brain states. The proposed architecture integrates algebraic topology with differential geometry to construct cohomological operators that generalize gradient-based learning within a homological landscape. Synthetic data with controlled topological signatures and real neural datasets are jointly analyzed using persistent homology, sheaf cohomology, and spectral Laplacians to quantify stability, continuity, and structural preservation. Empirical results demonstrate that the model achieves superior manifold consistency and noise resilience compared to graph neural and manifold-based deep architectures, establishing a coherent mathematical foundation for topology-driven representation learning.

📄 PDF Abstract BibTeX arXiv:2512.08241

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Fast Topological Signal Identification and Persistent Cohomological Cycle Matching

2022-09-30 · Inés García-Redondo, Anthea Monod, Anna Song

Within the context of topological data analysis, the problems of identifying topological significance and matching signals across datasets are important and useful inferential tasks in many applications. The limitation o…

CPUTopological Data Analysis

Algorithm for Interpretable Graph Features via Motivic Persistent Cohomology

2025-12-23 · Yoshihiro Maruyama arxiv

We present the Chromatic Persistence Algorithm (CPA), an event-driven method for computing persistent cohomological features of weighted graphs via graphic arrangements, a classical object in computational geometry. We e…

Topology-Guaranteed Image Segmentation: Enforcing Connectivity, Genus, and Width Constraints

2026-01-16 · Wenxiao Li, Xue-Cheng Tai, Jun Liu arxiv

Existing research highlights the crucial role of topological priors in image segmentation, particularly in preserving essential structures such as connectivity and genus. Accurately capturing these topological features o…

Image Segmentation

A higher homotopic extension of persistent (co)homology

2014-12-05 · Estanislao Herscovich

Our objective in this article is to show a possibly interesting structure of homotopic nature appearing in persistent (co)homology. Assuming that the filtration of the (say) simplicial set embedded in a finite dimensiona…

Topological Data Analysis

Learning Topological Representations for Deep Image Understanding

2024-03-22 · Xiaoling Hu

In many scenarios, especially biomedical applications, the correct delineation of complex fine-scaled structures such as neurons, tissues, and vessels is critical for downstream analysis. Despite the strong predictive po…

Deep LearningTopological Data Analysis