Essays about: "sparse vector"

Showing result 1 - 5 of 16 essays containing the words sparse vector.

  1. 1. GPS-Free UAV Geo-Localization Using a Reference 3D Database

    University essay from Linköpings universitet/Institutionen för systemteknik

    Author : Justus Karlsson; [2022]
    Keywords : Deep Learning; Machine Learning; ML; AI; UAV; GPS-Free; CNN; 3D CNN; GCNN; 3D Database; geolocalization; geo-localization; georegistration; Hidden Markov Model; HMM; satellite; satellite database; Batch-Hard; triplet loss; PyTorch Geometric;

    Abstract : The goal of this thesis has been global geolocalization using only visual input and a 3D database for reference. In recent years Convolutional Neural Networks (CNNs) have seen huge success in the task of classifying images. The flattened tensors at the final layers of a CNN can be viewed as vectors describing different input image features. READ MORE

  2. 2. Computation of posterior covariances of object points in bundle adjustment

    University essay from Umeå universitet/Institutionen för datavetenskap

    Author : Niklas Kallin; [2019]
    Keywords : ;

    Abstract : Bundle adjustment (BA) is a photogrammetric method for optimal estimation of parameters from image measurements. The parameters include 3D coordinates of objects points (OP). The result of the bundle adjustment process is a vector of estimates and its covariance matrix, C. The elements of this matrix contain quality indicators of the estimation. READ MORE

  3. 3. Compressed sensing for error correction on real-valued vectors

    University essay from Linnéuniversitetet/Institutionen för matematik (MA)

    Author : Pontus Tordsson; [2019]
    Keywords : compressed sensing; error correction; sparse vector; L0-minimization; L1-minimization;

    Abstract : Compressed sensing (CS) is a relatively new branch of mathematics with very interesting applications in signal processing, statistics and computer science. This thesis presents some theory of compressed sensing, which allows us to recover (high-dimensional) sparse vectors from (low-dimensional) compressed measurements by solving the L1-minimization problem. READ MORE

  4. 4. The Effect of Data Quantity on Dialog System Input Classification Models

    University essay from KTH/Hälsoinformatik och logistik

    Author : Johan Lipecki; Viggo Lundén; [2018]
    Keywords : Chatbot; Chatterbot; Virtual Assistant; Dialog System; Natural Language Understanding; Word Embedding; Word Vector Models; Text Classification; Chattbot; Virtuell Assistent; Dialogsystem; Naturlig språkbehandling; Ordinbäddning; Ordvektormodeller; Textklassificering;

    Abstract : This paper researches how different amounts of data affect different word vector models for classification of dialog system user input. A hypothesis is tested that there is a data threshold for dense vector models to reach the state-of-the-art performance that have been shown with recent research, and that character-level n-gram word-vector classifiers are especially suited for Swedish classifiers–because of compounding and the character-level n-gram model ability to vectorize out-of-vocabulary words. READ MORE

  5. 5. Analysis of GPU accelerated OpenCL applications on the Intel HD 4600 GPU

    University essay from Linköpings universitet/Programvara och system

    Author : Johnsson Arvid; [2017]
    Keywords : ;

    Abstract : GPU acceleration is the concept of accelerating the execution speed of an application by running it on the GPU. Researchers and developers have always wanted to achieve greater speed for their applications and GPU acceleration is a very common way of doing so. READ MORE