Essays about: "The impact of imbalanced training data for convolutional neural networks"

Found 3 essays containing the words The impact of imbalanced training data for convolutional neural networks.

  1. 1. Deep Learning for Semantic Segmentation of 3D Point Clouds from an Airborne LiDAR

    University essay from Linköpings universitet/Datorseende

    Author : Sabina Serra; [2020]
    Keywords : Deep Learning; Machine Learning; Computer vision; Semantic Segmentation; Unmanned Aerial Vehicle; UAV; LiDAR; Point Cloud; 3D Data; Point Cloud Segmentation; Point Classification; Pre-training; Convolutional Neural Network; CNN; Djupinlärning; maskininlärning; semantisk segmentering; LiDAR; datorseende; punktmoln;

    Abstract : Light Detection and Ranging (LiDAR) sensors have many different application areas, from revealing archaeological structures to aiding navigation of vehicles. However, it is challenging to interpret and fully use the vast amount of unstructured data that LiDARs collect. READ MORE

  3. 2. A systematic study of the class imbalance problem in convolutional neural networks

    University essay from KTH/Skolan för datavetenskap och kommunikation (CSC)

    Author : Mateusz Buda; [2017]
    Keywords : Class Imbalance; Convolutional Neural Networks; Deep Learning; Image Classification;

    Abstract : In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks and compare frequently used methods to address the issue. Class imbalance refers to significantly different number of examples among classes in a training set. READ MORE

  4. 3. The Impact of Imbalanced Training Data for Convolutional Neural Networks

    University essay from KTH/Skolan för datavetenskap och kommunikation (CSC)

    Author : David Masko; Paulina Hensman; [2015]
    Keywords : ;

    Abstract : This thesis empirically studies the impact of imbalanced training data on Convolutional Neural Network (CNN) performance in image classification. Images from the CIFAR-10 dataset, a set containing 60 000 images of 10 different classes, are used to create training sets with different distributions between the classes. READ MORE