paper-with-me

Papers

Graph-based Predictable Feature Analysis

2016-02-01 · Björn Weghenkel, Asja Fischer, Laurenz Wiskott

We propose graph-based predictable feature analysis (GPFA), a new method for unsupervised learning of predictable features from high-dimensional time series, where high predictability is understood very generically as low variance in the distribution of the next data point given the previous ones. We show how this measure of predictability can be understood in terms of graph embedding as well as how it relates to the information-theoretic measure of predictive information in special cases. We confirm the effectiveness of GPFA on different datasets, comparing it to three existing algorithms with similar objectives---namely slow feature analysis, forecastable component analysis, and predictable feature analysis---to which GPFA shows very competitive results.

📄 PDF Abstract BibTeX arXiv:1602.00554

Code (0)

등록된 구현이 없습니다.

Tasks

Graph EmbeddingTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

PFAx: Predictable Feature Analysis to Perform Control

2017-12-02 · Stefan Richthofer, Laurenz Wiskott

Predictable Feature Analysis (PFA) (Richthofer, Wiskott, ICMLA 2015) is an algorithm that performs dimensionality reduction on high dimensional input signal. It extracts those subsignals that are most predictable accordi…

Dimensionality Reductionfeature selectionglobal-optimizationReinforcement Learning

Predictable Feature Analysis

2013-11-11 · Stefan Richthofer, Laurenz Wiskott

Every organism in an environment, whether biological, robotic or virtual, must be able to predict certain aspects of its environment in order to survive or perform whatever task is intended. It needs a model that is capa…

Decision Making

SAGMAN: Stability Analysis of Graph Neural Networks on the Manifolds

2024-02-13 · Wuxinlin Cheng, Chenhui Deng, Ali Aghdaei, Zhiru Zhang 외

Modern graph neural networks (GNNs) can be sensitive to changes in the input graph structure and node features, potentially resulting in unpredictable behavior and degraded performance. In this work, we introduce a spect…

Dimensionality ReductionGraph EmbeddingRecommendation Systems

Modelling Quasi-Orthographic Captures for Surface Imaging

2023-05-14 · Maniratnam Mandal, Venkatesh K. Subramanian

Surveillance and surveying are two important applications of empirical research. A major part of terrain modelling is supported by photographic surveys which are used for capturing expansive natural surfaces using a wide…

Computational Efficiency

Transcoders for Investigating Deception in Language Models

2026-07-16 · Darius Lim, Nathan Leow, Xin Wei Chia arxiv

Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour. In this paper, we investigate the use of transcoders to analyse decepti…