Sökning: "16 bit"

Visar resultat 6 - 10 av 86 uppsatser innehållade orden 16 bit.

  1. 6. Representation and Efficient Computation of Sparse Matrix for Neural Networks in Customized Hardware

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Lihao Yan; [2022]
    Nyckelord :Convolutional neural networks; Sparse matrix representation; Model compression; Algorithm-hardware co-design; AlexNet; Konvolutionella neurala nätverk; Sparsam matrisrepresentation; Modellkomprimering; Algoritm-hårdvarusamdesign; AlexNet;

    Sammanfattning : Deep Neural Networks are widely applied to various kinds of fields nowadays. However, hundreds of thousands of neurons in each layer result in intensive memory storage requirement and a massive number of operations, making it difficult to employ deep neural networks on mobile devices where the hardware resources are limited. LÄS MER

  3. 7. Mapping quantized convolutional layers on the SiLago platform

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Yue Zhang; [2022]
    Nyckelord :SiLago; algorithm mapping; quantized neural networks; convolution; SiLago; algoritmkartläggning; kvantiserade neurala nätverk; faltning;

    Sammanfattning : Convolutional neural networks (CNNs) have been utilized in various applications, such as image classification, computer vision, etc. With development, the complexity and computation of CNNs also increase, which requires more memory and resources when deployed on devices, especially embedded systems. LÄS MER

  4. 8. Analys av förutsättningar för solceller på industri i Skellefteå

    Uppsats för yrkesexamina på grundnivå, Umeå universitet/Institutionen för tillämpad fysik och elektronik

    Författare :Jonathan Eriksson; [2022]
    Nyckelord :Solceller; fotovoltaik; Sverige;

    Sammanfattning : I denna rapport utvärderas lönsamheten hos en potentiell installation av solcellsmoduler på en industrilokal i Bureå strax utanför Skellefteå. Arbetet är utfört åt Pelimi Fastigheter AB i Skellefteå som är intresserade utav att energieffektivisera sina fastigheter, däribland Becurhuset som detta arbete innefattar. LÄS MER

  5. 9. Semantic segmentation of off-road scenery on embedded hardware using transfer learning

    Master-uppsats, KTH/Mekatronik

    Författare :Filip Elander; [2021]
    Nyckelord :Semantic Segmentation; forestry navigation; Deep Neural Network; autonomous navigation; residual neural network; Convolutional neural network; Semantisk Segmentering; Autonom Terrängnavigering; Residuala Nätverk; Konvolutionellt Neuralt Nätverk; Autonom navigering;

    Sammanfattning : Real-time semantic scene understanding is a challenging computer vision task for autonomous vehicles. A limited amount of research has been done regarding forestry and off-road scene understanding, as the industry focuses on urban and on-road applications. LÄS MER

  7. 10. RISC-V Based Application-Specific Instruction Set Processor for Packet Processing in Mobile Networks

    Master-uppsats, Linköpings universitet/Datorteknik

    Författare :Oskar Södergren; [2021]
    Nyckelord :eCPRI; ORAN; ASIP; fronthaul; RISC-V; bit manipulation; 5G; packet processing;

    Sammanfattning : This thesis explores the use of an ASIP for handling O-RAN control data. A model application was constructed, optimized and profiled on a simple RV32-IMC core. The compiled code was analyzed, and the instructions “byte swap”, “pack”, bitwise extract/deposit” and “bit field place” were implemented. LÄS MER