Sökning: "neural network"

Visar resultat 1 - 5 av 892 uppsatser innehållade orden neural network.

  1. 1. Machine Learning Based Prediction and Classification for Uplift Modeling

    Master-uppsats, KTH/Matematisk statistik; KTH/Matematisk statistik

    Författare :Lovisa Börthas; Jessica Krange Sjölander; [2020]
    Nyckelord :Uplift Modeling; Data Pre-Processing; Predictive Modeling; Incremental Modeling; Random Forests; Logistic Regression; Neural Networks; Ensemble Methods; Machine Learning; Multi-Layer Perceptron; Inkrementell responsanalys; databehandling; prediktiv modellering; random forests; logistisk regression; neurala nätverk; mulit-layer perceptron; ensemble metoder; maskininlärning;

    Sammanfattning : The desire to model the true gain from targeting an individual in marketing purposes has lead to the common use of uplift modeling. Uplift modeling requires the existence of a treatment group as well as a control group and the objective hence becomes estimating the difference between the success probabilities in the two groups. LÄS MER

  2. 2. An approach to automate accident scenario generation using recurrent neural networks

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

    Författare :Ludvig Oliver Gee; Ian Rhys Jenkins; [2019-11-26]
    Nyckelord :Machine Learning; Recurrent Neural Networks; Active Safety Systems; Scenario Generation; Testing; Time Series Prediction;

    Sammanfattning : There is a need to improve the test procedure of Active Safety Systems through the automation of scenario generation, especially accident scenarios that are critical for testing. The purpose of this thesis is to provide an approach to automate the test generation process using machine learning. LÄS MER

  3. 3. Deep Neural Network Compression for Object Detection and Uncertainty Quantification

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

    Författare :Mohammad Ahraz Asif; Georgios Tzelepis; [2019-11-21]
    Nyckelord :Deep Learning; Model Compression; Knowledge Distillation; Bayesian Deep Learning; Object Detection;

    Sammanfattning : Neural networks have been notorious for being computational expensive. Their demand for hardware resources prohibits their extensive use in embedded devices and puts restrictions on tasks like real time tracking. LÄS MER

  4. 4. Effects of Video Compression formats on Neural Network Performance

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

    Författare :Marko Stanoevich; Jonathan Partain; [2019-11-18]
    Nyckelord :;

    Sammanfattning : The field of autonomous vehicles and driverless carsis a field which makes extensive use of machine learning andartificial intelligence, relying on it to make decisions. Thesedecisions require a vast amount of data in order to be properlyinferred. LÄS MER

  5. 5. Fast visual grounding in interaction

    Master-uppsats, Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteori

    Författare :José Miguel Cano Santín; [2019-10-04]
    Nyckelord :grounding; object learning; interactive learning; transfer learning; neural networks;

    Sammanfattning : A big challenge for the development situated agents is that they need to be capable of grounding real objects of their enviroment to representations with semantic meaning, so they can be comunicated to human agents using the human language. de Graaf (2016) developed the KILLE framework, which is a static camerabasedrobot capable of learning objects and spatial relations from very few samples using image processing algorithms suitable for learning from few samples. LÄS MER