An energy efficient processor array and memory controller for accurate processing of convolutional neural network-based inference engines

Abstract Exploiting unstructured sparsity in the hardware accelerator of a Convolutional Neural Networks (CNNs) based inference can improve energy efficiency. However, it needs a complex controller for indexing and load-balancing. A controller for managing unstructured sparsity in Fully Connected (F...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	S. Deepika, V. Arunachalam
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	Nature Portfolio 2025-11-01
Σειρά:	Scientific Reports
Θέματα:	Convolutional neural network Dataflow Deep learning Energy-efficient accelerator Image classification Compression
Διαθέσιμο Online:	https://doi.org/10.1038/s41598-025-23303-5
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!