persistent homology
PulseAugur coverage of persistent homology — every cluster mentioning persistent homology across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New TopoCast framework evaluates structural fidelity in time series forecasting
Researchers have introduced TopoCast, a new framework designed to evaluate the structural fidelity of time series forecasts generated by transformer-based models. Unlike traditional metrics like mean squared error, whic…
-
Persistent homology tracks LLM representation changes during fine-tuning
Researchers have employed persistent homology to analyze the internal representation dynamics of large language models during supervised fine-tuning. Their study, which examined four transformer models (1B to 7B paramet…
-
New NMF Method Integrates Topology for Enhanced Data Interpretation
Researchers have developed a novel approach to Non-negative Matrix Factorisation (NMF) by incorporating topological regularisation. This method aims to improve the interpretability of learned bases by considering the to…
-
New Topological Method Enhances Molecular Dynamics Simulation Analysis
Researchers have introduced a novel method for analyzing molecular dynamics simulations using persistent homology (PH). This approach, which includes a protein-specific modification called the masked Flood complex, gene…
-
New metric measures AI receiver resilience to channel shifts
Researchers have developed a new metric called the Topological Resilience Index (TRI) to assess the robustness of AI-native wireless receivers. This index, based on persistent homology, quantifies the structural stabili…
-
PCA visualization limitations highlighted with fossil teeth data
Researchers have identified limitations in Principal Component Analysis (PCA) when applied to visualizing high-dimensional data that resides on a nonlinear manifold. Using a dataset of fossil teeth, they demonstrated th…
-
Topological method analyzes dynamic Bayesian networks
Researchers have developed a new topological method for analyzing dynamic Bayesian networks (DBNs). This approach associates a time-varying graph with each DBN, highlighting strong dependencies between variables. By app…
-
Topology research reveals neural network grokking signatures and architectural bypasses
Researchers are exploring the phenomenon of 'grokking' in neural networks, where models initially memorize data before generalizing. One study proposes modifying architectural topology, such as enforcing spherical const…
-
Researchers use persistent homology to map LLM latent space changes under adversarial attacks
Researchers have developed a new method using persistent homology to analyze the internal workings of Large Language Models (LLMs). This technique characterizes how adversarial inputs alter the geometric and topological…