Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765651011> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2765651011 abstract "The success of deep convolutional neural network (CNN) in computer vision especially image classification problems requests a new information theory for function of image, instead of image itself. In this article, after establishing a deep mathematical connection between image classification problem and quantum spin model, we propose to use entanglement entropy, a generalization of classical Boltzmann-Shannon entropy, as a powerful tool to characterize the information needed for representation of general function of image. We prove that there is a sub-volume-law bound for entanglement entropy of target functions of reasonable image classification problems. Therefore target functions of image classification only occupy a small subspace of the whole Hilbert space. As a result, a neural network with polynomial number of parameters is efficient for representation of such target functions of image. The concept of entanglement entropy can also be useful to characterize the expressive power of different neural networks. For example, we show that to maintain the same expressive power, number of channels $D$ in a convolutional neural network should scale with the number of convolution layers $n_c$ as $Dsim D_0^{frac{1}{n_c}}$. Therefore, deeper CNN with large $n_c$ is more efficient than shallow ones." @default.
- W2765651011 created "2017-11-10" @default.
- W2765651011 creator A5051487932 @default.
- W2765651011 date "2017-10-16" @default.
- W2765651011 modified "2023-09-27" @default.
- W2765651011 title "Entanglement Entropy of Target Functions for Image Classification and Convolutional Neural Network." @default.
- W2765651011 hasPublicationYear "2017" @default.
- W2765651011 type Work @default.
- W2765651011 sameAs 2765651011 @default.
- W2765651011 citedByCount "3" @default.
- W2765651011 countsByYear W27656510112017 @default.
- W2765651011 countsByYear W27656510112021 @default.
- W2765651011 crossrefType "posted-content" @default.
- W2765651011 hasAuthorship W2765651011A5051487932 @default.
- W2765651011 hasConcept C106301342 @default.
- W2765651011 hasConcept C11413529 @default.
- W2765651011 hasConcept C115961682 @default.
- W2765651011 hasConcept C121040770 @default.
- W2765651011 hasConcept C121332964 @default.
- W2765651011 hasConcept C153180895 @default.
- W2765651011 hasConcept C154945302 @default.
- W2765651011 hasConcept C192576344 @default.
- W2765651011 hasConcept C32834561 @default.
- W2765651011 hasConcept C33923547 @default.
- W2765651011 hasConcept C41008148 @default.
- W2765651011 hasConcept C50644808 @default.
- W2765651011 hasConcept C62520636 @default.
- W2765651011 hasConcept C75294576 @default.
- W2765651011 hasConcept C80444323 @default.
- W2765651011 hasConcept C81363708 @default.
- W2765651011 hasConcept C84114770 @default.
- W2765651011 hasConceptScore W2765651011C106301342 @default.
- W2765651011 hasConceptScore W2765651011C11413529 @default.
- W2765651011 hasConceptScore W2765651011C115961682 @default.
- W2765651011 hasConceptScore W2765651011C121040770 @default.
- W2765651011 hasConceptScore W2765651011C121332964 @default.
- W2765651011 hasConceptScore W2765651011C153180895 @default.
- W2765651011 hasConceptScore W2765651011C154945302 @default.
- W2765651011 hasConceptScore W2765651011C192576344 @default.
- W2765651011 hasConceptScore W2765651011C32834561 @default.
- W2765651011 hasConceptScore W2765651011C33923547 @default.
- W2765651011 hasConceptScore W2765651011C41008148 @default.
- W2765651011 hasConceptScore W2765651011C50644808 @default.
- W2765651011 hasConceptScore W2765651011C62520636 @default.
- W2765651011 hasConceptScore W2765651011C75294576 @default.
- W2765651011 hasConceptScore W2765651011C80444323 @default.
- W2765651011 hasConceptScore W2765651011C81363708 @default.
- W2765651011 hasConceptScore W2765651011C84114770 @default.
- W2765651011 hasLocation W27656510111 @default.
- W2765651011 hasOpenAccess W2765651011 @default.
- W2765651011 hasPrimaryLocation W27656510111 @default.
- W2765651011 hasRelatedWork W1878638972 @default.
- W2765651011 hasRelatedWork W1922629554 @default.
- W2765651011 hasRelatedWork W2092582833 @default.
- W2765651011 hasRelatedWork W2545012676 @default.
- W2765651011 hasRelatedWork W2546515640 @default.
- W2765651011 hasRelatedWork W2560504092 @default.
- W2765651011 hasRelatedWork W2584280040 @default.
- W2765651011 hasRelatedWork W2612616507 @default.
- W2765651011 hasRelatedWork W2739240958 @default.
- W2765651011 hasRelatedWork W2897316208 @default.
- W2765651011 hasRelatedWork W2936232398 @default.
- W2765651011 hasRelatedWork W2963918359 @default.
- W2765651011 hasRelatedWork W2977118166 @default.
- W2765651011 hasRelatedWork W2980611702 @default.
- W2765651011 hasRelatedWork W2980702925 @default.
- W2765651011 hasRelatedWork W3007598458 @default.
- W2765651011 hasRelatedWork W3101895620 @default.
- W2765651011 hasRelatedWork W3160146370 @default.
- W2765651011 hasRelatedWork W3182223998 @default.
- W2765651011 hasRelatedWork W3193396833 @default.
- W2765651011 isParatext "false" @default.
- W2765651011 isRetracted "false" @default.
- W2765651011 magId "2765651011" @default.
- W2765651011 workType "article" @default.