paper-with-me

Papers

Improved graph-based SFA: Information preservation complements the slowness principle

2016-01-15 · Alberto N. Escalante-B., Laurenz Wiskott

Slow feature analysis (SFA) is an unsupervised-learning algorithm that extracts slowly varying features from a multi-dimensional time series. A supervised extension to SFA for classification and regression is graph-based SFA (GSFA). GSFA is based on the preservation of similarities, which are specified by a graph structure derived from the labels. It has been shown that hierarchical GSFA (HGSFA) allows learning from images and other high-dimensional data. The feature space spanned by HGSFA is complex due to the composition of the nonlinearities of the nodes in the network. However, we show that the network discards useful information prematurely before it reaches higher nodes, resulting in suboptimal global slowness and an under-exploited feature space. To counteract these problems, we propose an extension called hierarchical information-preserving GSFA (HiGSFA), where information preservation complements the slowness-maximization goal. We build a 10-layer HiGSFA network to estimate human age from facial photographs of the MORPH-II database, achieving a mean absolute error of 3.50 years, improving the state-of-the-art performance. HiGSFA and HGSFA support multiple-labels and offer a rich feature space, feed-forward training, and linear complexity in the number of samples and dimensions. Furthermore, HiGSFA outperforms HGSFA in terms of feature slowness, estimation accuracy and input reconstruction, giving rise to a promising hierarchical supervised-learning approach.

📄 PDF Abstract BibTeX arXiv:1601.03945

Code (0)

등록된 구현이 없습니다.

Tasks

MORPHTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Travel time tomography with adaptive dictionaries

2017-12-16 · Michael Bianco, Peter Gerstoft

We develop a 2D travel time tomography method which regularizes the inversion by modeling groups of slowness pixels from discrete slowness maps, called patches, as sparse linear combinations of atoms from a dictionary. W…

Dictionary Learning

Uncertainty and Explainable Analysis of Machine Learning Model for Reconstruction of Sonic Slowness Logs

2023-08-24 · Hua Wang, Yuqiong Wu, Yushun Zhang, Fuqiang Lai 외

Logs are valuable information for oil and gas fields as they help to determine the lithology of the formations surrounding the borehole and the location and reserves of subsurface oil and gas reservoirs. However, importa…

Ensemble Learning

Temporal Slowness in Central Vision Drives Semantic Object Learning

2026-02-04 · Timothy Schaumlöffel, Arthur Aubret, Gemma Roig, Jochen Triesch arxiv

Humans acquire semantic object representations from egocentric visual streams with minimal supervision, but the underlying mechanisms remain unclear. Importantly, the visual system only processes the center of its field …

Self-Supervised Learning

Reading Comprehension with Graph-based Temporal-Casual Reasoning

2018-08-01 · COLING 2018 8 · Yawei Sun, Gong Cheng, Yuzhong Qu

Complex questions in reading comprehension tasks require integrating information from multiple sentences. In this work, to answer such questions involving temporal and causal relations, we generate event graphs from text…

Dependency ParsingReading Comprehension

Autoencoding Slow Representations for Semi-supervised Data Efficient Regression

2020-12-11 · Oliver Struckmeier, Kshitij Tiwari, Ville Kyrki

The slowness principle is a concept inspired by the visual cortex of the brain. It postulates that the underlying generative factors of a quickly varying sensory signal change on a slower time scale. Unsupervised learnin…

regressionRepresentation Learning