
Delve into advanced Graph Neural Network concepts, exploring topological message passing, simplicial complexes, and high-dimensional interactions for computational graph networks and molecular design applications.

Explore persistent homology rank functions through PCA, featuring case studies and insights into topological data analysis techniques.

Explore molecular dynamics simulations and machine learning techniques to analyze interfacial hydrophobicity, focusing on efficient data analysis methods and topological approaches for complex chemical systems.

Explore deep learning's interaction with Topological Data Analysis, focusing on explainability and performance enhancement in neural networks and various data analysis applications.

Explore the topological constraints of neural network architectures and their impact on function representation, with insights from recent research and ongoing work in the field.

Explore unsupervised learning and topological data analysis to uncover hidden insights in complex datasets, with applications in health and finance using Python and R.

Explore advanced Topological Data Analysis through multiparameter persistence, focusing on practical machine learning applications using MMA decomposition and signed barcode techniques.

Explore topological data analysis applications in art perception, comparing responses to abstract paintings and AI-generated images through eye movement analysis and geometric feature recognition.

Explore metric geometry of persistence diagram spaces, focusing on synthetic curvature bounds and applications in non-smooth, infinite-dimensional contexts.

Explore persistent homology for analyzing phase transitions in complex physical systems. Learn how this topological machine learning method extracts meaningful information from sparse data in condensed matter physics.

Explore topological data analysis applications in visual art perception, comparing eye movements for abstract paintings vs. AI-generated images using algebraic topology methods.

Explore persistent homology in plant-pollinator interactions, analyzing topological features and the impact of flowering plant surveys on understanding community structures.

Exploring metric space magnitude in neural networks: new topological complexity measures for assessing generalization capabilities, with applications to transformers and deep graph networks.

Explore V-Mapper, an innovative method for analyzing single-cell gene expression data. Learn how it extracts topology and flow of cell differentiation, enhancing trajectory inference in high-dimensional spaces.

Explore temporal hypergraphs and zigzag persistence to analyze complex systems' topological evolution, applied to cybersecurity and social networks for understanding underlying dynamics.

Spectral relaxations of persistent rank invariant: A framework for continuous relaxations, offering stability and differentiability while preserving key properties and enabling efficient GPU-parallelized computation.

Explore the connection between persistent homology and discrete Morse theory, unifying key concepts and applying insights to shape reconstruction in computational topology.

Exploring topological data analysis for pattern quantification, model comparison, and feature design in zebrafish skin patterns and other complex systems.

Explore geometric properties and descent dynamics in random landscapes, focusing on theoretical insights and practical applications in complex systems.

Explore applications of topological data analysis in cancer research, focusing on mathematical modeling of treatments, resistance, and optimization.

Czy AI zrobi z nas superbohaterów? Nie. Ale jeśli nauczymy się z nim współpracować – delegować, łączyć cele i koordynować przepływ informacji – możemy działać szybciej, mądrzej i odważniej. W tej prelekcji pokażę, jak przygotować się na przyszłość, w której technologia i człowiek grają w jednej druż