Sökning: "inference engine"

Visar resultat 1 - 5 av 14 uppsatser innehållade orden inference engine.

  1. 1. Using Quantization and Serialization to Improve AI Super-Resolution Inference Time on Cloud Platform

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

    Författare :Wai-Hong Anton Fu; [2023]
    Nyckelord :;

    Sammanfattning : AI Super-Resolution is a branch of Artificial Intelligence where the goal is to take a low-resolution image and upscale it into a high-resolution image. These models are usually deep learning models based on Convolutional Neural Networks (CNN) and/or transformers. LÄS MER

  3. 2. Flight search engine CPU consumption prediction

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

    Författare :Zhaopeng Tao; [2021]
    Nyckelord :Flight Search Engine; Deep Neural Networks; Tabular Data; Regression; Machine Learning; Flight Schedule Embedding; Node Embedding; Graph Embedding; Line Graph Embedding; Sökmotor för flygresor; Djupa neurala nätverk; Tabulära data; Regression; Maskininlärning; Inbäddning av flygschema; Inbäddning av noder; Inbäddning av grafer; Inbäddning av linjediagram;

    Sammanfattning : The flight search engine is a technology used in the air travel industry. It allows the traveler to search and book for the best flight options, such as the combination of flights while keeping the best services, options, and price. The computation for a flight search query can be very intensive given its parameters and complexity. LÄS MER

  4. 3. Concept and Architecture of a Decision Support System for Regulation of Diuretics in Chronic Heart Failure Patients

    Master-uppsats, Lunds universitet/Avdelningen för Biomedicinsk teknik

    Författare :Ellinor Runquist; [2021]
    Nyckelord :Technology and Engineering;

    Sammanfattning : Fluid overload is the build up of excessive fluid in the body and is a common condition amongst chronic heart failure patients. Fluid overload is treated with diuretics but the level of excessive fluid can vary. LÄS MER

  5. 4. 2D object detection and semantic segmentation in the Carla simulator

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

    Författare :Chen Wang; [2020]
    Nyckelord :Object-detectiopn; Semantic segmentation; Yolov4; ESPnetv2; Carla; Objekt-detectiopn; semantisk segmentering; Yolov4; ESPnetv2; Carla;

    Sammanfattning : The subject of self-driving car technology has drawn growing interest in recent years. Many companies, such as Baidu and Tesla, have already introduced automatic driving techniques in their newest cars when driving in a specific area. However, there are still many challenges ahead toward fully autonomous driving cars. LÄS MER

  7. 5. BRB based Deep Learning Approach with Application in Sensor Data Streams

    Master-uppsats, Luleå tekniska universitet/Datavetenskap

    Författare :Sami Kabir; [2019]
    Nyckelord :BRBES; Deep Learning; integration; sensor data; predict;

    Sammanfattning : Predicting events based on available data is an effective way to protect human lives. Issuing health alert based on prediction of environmental pollution, executing timely evacuation of people from vulnerable areas based on prediction of natural disasters are the application areas of sensor data stream where accurate and timely prediction is crucial to safeguard people and assets. LÄS MER