Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385819989> ?p ?o ?g. }
- W4385819989 endingPage "93" @default.
- W4385819989 startingPage "1" @default.
- W4385819989 abstract "The deep neural network (DNN) has shown impressive performance in various applications such as computer vision and natural language processing. However, such high performance of DNN comes at a high computational cost. For calculating DNN, a large size of weight and feature map should be stored in memory and multiplied by each other after being loaded from memory. Recently, the portion of memory access for the total time and total power consumption has been increased in the DNN accelerators, due to the stagnant improvement of memory, which is known as the “memory wall” problem. Especially in the case of deep reinforcement learning, memory optimization is essential because it has mainly utilized multiple numbers of fully connected layers simultaneously. In this chapter, we propose a deep reinforcement learning accelerator that optimizes memory bandwidth and memory power consumption. The proposed accelerator optimizes memory bandwidth by dual-mode weight compression and optimizes memory power consumption with floating-point in-memory computing architecture." @default.
- W4385819989 created "2023-08-15" @default.
- W4385819989 creator A5010104451 @default.
- W4385819989 creator A5077896259 @default.
- W4385819989 date "2023-01-01" @default.
- W4385819989 modified "2023-09-26" @default.
- W4385819989 title "Deep Reinforcement Learning Processor Design for Mobile Applications" @default.
- W4385819989 cites W1919191429 @default.
- W4385819989 cites W2117539524 @default.
- W4385819989 cites W2145339207 @default.
- W4385819989 cites W2194775991 @default.
- W4385819989 cites W2289252105 @default.
- W4385819989 cites W2609009256 @default.
- W4385819989 cites W2742454413 @default.
- W4385819989 cites W2766447205 @default.
- W4385819989 cites W2774669597 @default.
- W4385819989 cites W2903841424 @default.
- W4385819989 cites W2905100748 @default.
- W4385819989 cites W2907537824 @default.
- W4385819989 cites W2920954974 @default.
- W4385819989 cites W2921918777 @default.
- W4385819989 cites W2921967969 @default.
- W4385819989 cites W2922086978 @default.
- W4385819989 cites W2928560789 @default.
- W4385819989 cites W2945146780 @default.
- W4385819989 cites W2950656546 @default.
- W4385819989 cites W2962834855 @default.
- W4385819989 cites W2968983352 @default.
- W4385819989 cites W2970143800 @default.
- W4385819989 cites W2976137532 @default.
- W4385819989 cites W2978696242 @default.
- W4385819989 cites W2981849318 @default.
- W4385819989 cites W2982316857 @default.
- W4385819989 cites W2997502221 @default.
- W4385819989 cites W2999204576 @default.
- W4385819989 cites W3015729306 @default.
- W4385819989 cites W3016021860 @default.
- W4385819989 cites W3020965190 @default.
- W4385819989 cites W3088811935 @default.
- W4385819989 cites W3109309915 @default.
- W4385819989 cites W3128966520 @default.
- W4385819989 cites W3134304371 @default.
- W4385819989 cites W3174945061 @default.
- W4385819989 cites W3181651498 @default.
- W4385819989 cites W3183385172 @default.
- W4385819989 cites W3207033168 @default.
- W4385819989 cites W32403112 @default.
- W4385819989 cites W4220972538 @default.
- W4385819989 cites W4294691329 @default.
- W4385819989 doi "https://doi.org/10.1007/978-3-031-36793-9_1" @default.
- W4385819989 hasPublicationYear "2023" @default.
- W4385819989 type Work @default.
- W4385819989 citedByCount "0" @default.
- W4385819989 crossrefType "book-chapter" @default.
- W4385819989 hasAuthorship W4385819989A5010104451 @default.
- W4385819989 hasAuthorship W4385819989A5077896259 @default.
- W4385819989 hasConcept C108583219 @default.
- W4385819989 hasConcept C118524514 @default.
- W4385819989 hasConcept C121332964 @default.
- W4385819989 hasConcept C149635348 @default.
- W4385819989 hasConcept C154945302 @default.
- W4385819989 hasConcept C163258240 @default.
- W4385819989 hasConcept C171675096 @default.
- W4385819989 hasConcept C173608175 @default.
- W4385819989 hasConcept C176649486 @default.
- W4385819989 hasConcept C188045654 @default.
- W4385819989 hasConcept C2776257435 @default.
- W4385819989 hasConcept C2779602883 @default.
- W4385819989 hasConcept C2781357197 @default.
- W4385819989 hasConcept C2984118289 @default.
- W4385819989 hasConcept C31258907 @default.
- W4385819989 hasConcept C41008148 @default.
- W4385819989 hasConcept C50644808 @default.
- W4385819989 hasConcept C57863822 @default.
- W4385819989 hasConcept C62520636 @default.
- W4385819989 hasConcept C63511323 @default.
- W4385819989 hasConcept C82687282 @default.
- W4385819989 hasConcept C9390403 @default.
- W4385819989 hasConcept C97541855 @default.
- W4385819989 hasConcept C98986596 @default.
- W4385819989 hasConceptScore W4385819989C108583219 @default.
- W4385819989 hasConceptScore W4385819989C118524514 @default.
- W4385819989 hasConceptScore W4385819989C121332964 @default.
- W4385819989 hasConceptScore W4385819989C149635348 @default.
- W4385819989 hasConceptScore W4385819989C154945302 @default.
- W4385819989 hasConceptScore W4385819989C163258240 @default.
- W4385819989 hasConceptScore W4385819989C171675096 @default.
- W4385819989 hasConceptScore W4385819989C173608175 @default.
- W4385819989 hasConceptScore W4385819989C176649486 @default.
- W4385819989 hasConceptScore W4385819989C188045654 @default.
- W4385819989 hasConceptScore W4385819989C2776257435 @default.
- W4385819989 hasConceptScore W4385819989C2779602883 @default.
- W4385819989 hasConceptScore W4385819989C2781357197 @default.
- W4385819989 hasConceptScore W4385819989C2984118289 @default.
- W4385819989 hasConceptScore W4385819989C31258907 @default.
- W4385819989 hasConceptScore W4385819989C41008148 @default.
- W4385819989 hasConceptScore W4385819989C50644808 @default.
- W4385819989 hasConceptScore W4385819989C57863822 @default.