FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2908819435> ?p ?o ?g. }

• W2908819435 abstract "Compressed sensing algorithms recover a signal from its under-determined linear measurements by exploiting its structure. Starting from sparsity, recovery methods have steadily moved towards more complex structures. Recently, the emerging machine learning techniques, especially the generative models based on neural nets, potentially, can learn general complex structures. Inspired by the success of such models in various computer vision tasks, researchers in compressed sensing have recently started to employ them to design efficient recovery methods. Consider a generative model defined as function $g:{cal U}^kto{R}^n$, ${cal U}subset{R}$. Assume that the function $g$ is trained such that it can describe a class of desired signals ${cal Q}subset{R}^n$. The standard problem in noiseless compressed sensing is to recover ${bf x}in{cal Q}$ from under-determined linear measurements ${bf y}=A{bf x}$, where ${bf y}in{R}^m$ and $mll n$. A recovery method based on $g$ finds $g({bf u})$, $in{cal U}^k$, which has the minimum measurement error. In this paper, the performance of such a recovery method is studied and it is proven that, if the number of measurements ($m$) is larger than twice the dimension of the generative model ($k$), then ${bf x}$ can be recovered from ${bf y}$, with a distortion that is a function of the distortion induced by $g$ in describing $bf x$, i.e. $min_{{bf u}in{cal U}^k}|g({bf u})-{bf x}|$. To derive an efficient method, an algorithm based on projected gradient descent is proposed. It is proven that, given enough measurements, the algorithm converges to the optimal solution and is robust to measurement noise. Numerical results showing the effectiveness of the proposed method are presented." @default.
• W2908819435 created "2019-01-25" @default.
• W2908819435 creator A5015431603 @default.
• W2908819435 creator A5036465084 @default.
• W2908819435 date "2019-01-15" @default.
• W2908819435 modified "2023-09-27" @default.
• W2908819435 title "Using auto-encoders for solving ill-posed linear inverse problems" @default.
• W2908819435 cites W2028349405 @default.
• W2908819435 cites W2073354919 @default.
• W2908819435 cites W2098666275 @default.
• W2908819435 cites W2129131372 @default.
• W2908819435 cites W2135046866 @default.
• W2908819435 cites W2145096794 @default.
• W2908819435 cites W2181347294 @default.
• W2908819435 cites W2273561594 @default.
• W2908819435 cites W2296616510 @default.
• W2908819435 cites W2574952845 @default.
• W2908819435 cites W2578009003 @default.
• W2908819435 cites W2595294663 @default.
• W2908819435 cites W2604885021 @default.
• W2908819435 cites W2619204584 @default.
• W2908819435 cites W2783760338 @default.
• W2908819435 cites W2919115771 @default.
• W2908819435 cites W2963322354 @default.
• W2908819435 cites W2963742180 @default.
• W2908819435 cites W2964251511 @default.
• W2908819435 hasPublicationYear "2019" @default.
• W2908819435 type Work @default.
• W2908819435 sameAs 2908819435 @default.
• W2908819435 citedByCount "1" @default.
• W2908819435 countsByYear W29088194352020 @default.
• W2908819435 crossrefType "posted-content" @default.
• W2908819435 hasAuthorship W2908819435A5015431603 @default.
• W2908819435 hasAuthorship W2908819435A5036465084 @default.
• W2908819435 hasConcept C11413529 @default.
• W2908819435 hasConcept C114614502 @default.
• W2908819435 hasConcept C124851039 @default.
• W2908819435 hasConcept C126780896 @default.
• W2908819435 hasConcept C134306372 @default.
• W2908819435 hasConcept C135252773 @default.
• W2908819435 hasConcept C14036430 @default.
• W2908819435 hasConcept C153258448 @default.
• W2908819435 hasConcept C154945302 @default.
• W2908819435 hasConcept C167966045 @default.
• W2908819435 hasConcept C194257627 @default.
• W2908819435 hasConcept C207467116 @default.
• W2908819435 hasConcept C2524010 @default.
• W2908819435 hasConcept C2776257435 @default.
• W2908819435 hasConcept C33676613 @default.
• W2908819435 hasConcept C33923547 @default.
• W2908819435 hasConcept C39890363 @default.
• W2908819435 hasConcept C41008148 @default.
• W2908819435 hasConcept C50644808 @default.
• W2908819435 hasConcept C76155785 @default.
• W2908819435 hasConcept C78458016 @default.
• W2908819435 hasConcept C86803240 @default.
• W2908819435 hasConceptScore W2908819435C11413529 @default.
• W2908819435 hasConceptScore W2908819435C114614502 @default.
• W2908819435 hasConceptScore W2908819435C124851039 @default.
• W2908819435 hasConceptScore W2908819435C126780896 @default.
• W2908819435 hasConceptScore W2908819435C134306372 @default.
• W2908819435 hasConceptScore W2908819435C135252773 @default.
• W2908819435 hasConceptScore W2908819435C14036430 @default.
• W2908819435 hasConceptScore W2908819435C153258448 @default.
• W2908819435 hasConceptScore W2908819435C154945302 @default.
• W2908819435 hasConceptScore W2908819435C167966045 @default.
• W2908819435 hasConceptScore W2908819435C194257627 @default.
• W2908819435 hasConceptScore W2908819435C207467116 @default.
• W2908819435 hasConceptScore W2908819435C2524010 @default.
• W2908819435 hasConceptScore W2908819435C2776257435 @default.
• W2908819435 hasConceptScore W2908819435C33676613 @default.
• W2908819435 hasConceptScore W2908819435C33923547 @default.
• W2908819435 hasConceptScore W2908819435C39890363 @default.
• W2908819435 hasConceptScore W2908819435C41008148 @default.
• W2908819435 hasConceptScore W2908819435C50644808 @default.
• W2908819435 hasConceptScore W2908819435C76155785 @default.
• W2908819435 hasConceptScore W2908819435C78458016 @default.
• W2908819435 hasConceptScore W2908819435C86803240 @default.
• W2908819435 hasLocation W29088194351 @default.
• W2908819435 hasOpenAccess W2908819435 @default.
• W2908819435 hasPrimaryLocation W29088194351 @default.
• W2908819435 hasRelatedWork W1512467539 @default.
• W2908819435 hasRelatedWork W1800378265 @default.
• W2908819435 hasRelatedWork W1969815718 @default.
• W2908819435 hasRelatedWork W1998374554 @default.
• W2908819435 hasRelatedWork W2022611944 @default.
• W2908819435 hasRelatedWork W2134615334 @default.
• W2908819435 hasRelatedWork W2417107316 @default.
• W2908819435 hasRelatedWork W2619269121 @default.
• W2908819435 hasRelatedWork W2752422657 @default.
• W2908819435 hasRelatedWork W2777843033 @default.
• W2908819435 hasRelatedWork W2797553966 @default.
• W2908819435 hasRelatedWork W2922161739 @default.
• W2908819435 hasRelatedWork W2949413129 @default.
• W2908819435 hasRelatedWork W2949634346 @default.
• W2908819435 hasRelatedWork W2953014734 @default.
• W2908819435 hasRelatedWork W2976686232 @default.
• W2908819435 hasRelatedWork W2996484635 @default.
• W2908819435 hasRelatedWork W3017118217 @default.
• W2908819435 hasRelatedWork W3045507430 @default.

• next