Sökning: "deep neural networks"

Visar resultat 1 - 5 av 386 uppsatser innehållade orden deep neural networks.

  1. 1. Resource Optimal Neural Networks for Safety-critical Real-time Systems

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Joakim Åkerström; [2020-07-10]
    Nyckelord :Data science; machine learning; deep learning; neural networks; network compression; network acceleration; safety-critical systems; real-time systems;

    Sammanfattning : Deep neural networks consume an excessive amount of hardware resources, makingthem difficult to deploy to real-time systems. Previous work in the field of networkcompression lack the explicit hardware feedback necessary to control the resourceconstraints imposed by such systems. LÄS MER

  2. 2. Text analysis for email multi label classification

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Kyriaki Paniskaki; Sanjit Harsha Kadam; [2020-07-08]
    Nyckelord :natural language processing; machine learning; multi label text classification; deep neural networks; bilingual texts; emails; short texts;

    Sammanfattning : This master’s thesis studies a multi label text classification task on a small dataset of bilingual, English and Swedish, short texts (emails). Specifically, the size ofthe data set is 5800 emails and those emails are distributed among 107 classes withthe special case that the majority of the emails includes the two languages at thesame time. LÄS MER

  3. 3. Deep Learning and the Heston Model:Calibration & Hedging

    Kandidat-uppsats, Göteborgs universitet/Institutionen för nationalekonomi med statistik

    Författare :Oliver Klingberg Malmer; Victor Tisell; [2020-07-03]
    Nyckelord :deep learning; deep hedging; deep calibration; option pricing; stochastic volatilty; Heston model; S P 500 index options; incomplete markets; transaction costs;

    Sammanfattning : The computational speedup of computers has been one of the de ning characteristicsof the 21st century. This has enabled very complex numerical methods for solving existingproblems. As a result, one area that has seen an extraordinary rise in popularity over the lastdecade is what is called deep learning. LÄS MER

  4. 4. Implementation of a Deep Learning Inference Accelerator on the FPGA.

    Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

    Författare :Shenbagaraman Ramakrishnan; [2020]
    Nyckelord :Artificial Intelligence; Machine Learning; Deep Learning; Neural Networks; Deep Learning Accelerators; NVDLA; FPGA; Technology and Engineering;

    Sammanfattning : Today, Artificial Intelligence is one of the most important technologies, ubiquitous in our daily lives. Deep Neural Networks (DNN's) have come up as state of art for various machine intelligence applications such as object detection, image classification, face recognition and performs myriad of activities with exceptional prediction accuracy. LÄS MER

  5. 5. Deep Learning for Anomaly Detection in Microwave Links : Challenges and Impact on Weather Classification

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

    Författare :Olof Engström; [2020]
    Nyckelord :Anomaly Detection; Time Series; Forecasting; Weather Classification; Microwave Link; CNN; LSTM; Avvikelsedetektering; Tidsserier; Prognostisering; Väderklassificering; Mikrovågslänkar; faltningsnätverk; CNN; LSTM;

    Sammanfattning : Artificial intelligence is receiving a great deal of attention in various fields of science and engineering due to its promising applications. In today’s society, weather classification models with high accuracy are of utmost importance. LÄS MER