Essays about: "sequence to sequence learning"

Showing result 1 - 5 of 61 essays containing the words sequence to sequence learning.

  1. 1. Region Proposal Based Object Detectors Integrated With an Extended Kalman Filter for a Robust Detect-Tracking Algorithm

    University essay from Karlstads universitet/Fakulteten för hälsa, natur- och teknikvetenskap (from 2013)

    Author : Gabriel Khajo; [2019]
    Keywords : Object Detection; Extended Kalman Filter; Tracking;

    Abstract : In this thesis we present a detect-tracking algorithm (see figure 3.1) that combines the detection robustness of static region proposal based object detectors, like the faster region convolutional neural network (R-CNN) and the region-based fully convolutional networks (R-FCN) model, with the tracking prediction strength of extended Kalman filters, by using, what we have called, a translating and non-rigid user input region of interest (RoI-) mapping. READ MORE

  2. 2. Animal ID Tag Recognition with Convolutional and Recurrent Neural Network : Identifying digits from a number sequence with RCNN

    University essay from Högskolan i Skövde/Institutionen för informationsteknologi; Högskolan i Skövde/Institutionen för informationsteknologi

    Author : Issa Hijazi; Pontus Pettersson; [2019]
    Keywords : Machine Learning; Convolutional Neural Network; Recurrent Neural Network; Transfer learning; Microsoft Azure;

    Abstract : Major advances in machine learning have made image recognition applications, with Artificial Neural Network, blossom over the recent years. The aim of this thesis was to find a solution to recognize digits from a number sequence on an ID tag, used to identify farm animals, with the help of image recognition. READ MORE

  3. 3. Deep Imitation Learning on Spatio-Temporal Data with Multiple Adversarial Agents Applied on Soccer

    University essay from Linköpings universitet/Databas och informationsteknik

    Author : Per Lindström; [2019]
    Keywords : imitation learning; soccer; trajectory; deep learning; lstm;

    Abstract : Recently, the availability of high quality and high resolution spatio-temporal data has increased for many sports. This enabled deep analysis of player behaviour and game strategy. READ MORE

  4. 4. Multilabel text classification of public procurements using deep learning intent detection

    University essay from KTH/Matematisk statistik

    Author : Adin Suta; [2019]
    Keywords : Natural language processing; text classification; deep learning; applied mathematics; recurrent neural network; word embedding; Maskininlärning; textklassificering; artificiella neruonnät; tillämpad matematik;

    Abstract : Textual data is one of the most widespread forms of data and the amount of such data available in the world increases at a rapid rate. Text can be understood as either a sequence of characters or words, where the latter approach is the most common. READ MORE

  5. 5. Deep Learning-Based Automated Segmentation and Detection of Chondral Lesions on the Distal Femur

    University essay from KTH/Fysik

    Author : Josefin Lindemalm Karlsson; [2019]
    Keywords : Deep Learning; Machine Learning; automated segmentation; MRI; chondral lesions; articular cartilage; Deep Learning; Maskininlärning; automatiserad segmentering; MRI; broskskador; ledbrosk;

    Abstract : Articular chondral lesions in the knee joint can be diagnosed at an early stage using MRI. Segmenting and visualizing lesions and the overall joint structure allows improved communication between the radiologist and referring physician. It can also be of help when determining diagnosis or conducting surgical planning. READ MORE