Výsledky vyhledávání

Report

Active Face Frontalization using Commodity Unmanned Aerial Vehicles

Autor: Lakshminarayana, Nagashri, Liu, Yifang, Dantu, Karthik, Govindaraju, Venu, Napp, Nils

This paper describes a system by which Unmanned Aerial Vehicles (UAVs) can gather high-quality face images that can be used in biometric identification tasks. Success in face-based identification depends in large part on the image quality, and a majo

Externí odkaz: http://arxiv.org/abs/2102.08542

Zobrazit plný text záznamu

Report

Entropy-Isomap: Manifold Learning for High-dimensional Dynamic Processes

Autor: Schoeneman, Frank, Chandola, Varun, Napp, Nils, Wodo, Olga, Zola, Jaroslaw

Scientific and engineering processes deliver massive high-dimensional data sets that are generated as non-linear transformations of an initial state and few process parameters. Mapping such data to a low-dimensional manifold facilitates better unders

Externí odkaz: http://arxiv.org/abs/1802.06823

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Report

Error Metrics for Learning Reliable Manifolds from Streaming Data

Autor: Schoeneman, Frank, Mahapatra, Suchismit, Chandola, Varun, Napp, Nils, Zola, Jaroslaw

Spectral dimensionality reduction is frequently used to identify low-dimensional structure in high-dimensional data. However, learning manifolds, especially from the streaming data, is computationally and memory expensive. In this paper, we argue tha

Externí odkaz: http://arxiv.org/abs/1611.04067

Zobrazit plný text záznamu

Report

On Optimality Conditions for Auto-Encoder Signal Recovery

Autor: Arpit, Devansh, Zhou, Yingbo, Ngo, Hung Q., Napp, Nils, Govindaraju, Venu

Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost. The useful representations learned are often found to be sparse and distributed. On the other hand, compressed sensing and sparse

Externí odkaz: http://arxiv.org/abs/1605.07145

Zobrazit plný text záznamu