Essays about: "unlabeled"

Showing result 1 - 5 of 92 essays containing the word unlabeled.

  1. 1. Active learning for text classification in cyber security

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Amanda Carp; [2023]
    Keywords : Interactive machine learning; Active learning; Cost-effective active learning; Cyber environment; Interaktiv maskininlärning; Aktiv inlärning; Kostnadseffektiv aktiv inlärning; Cyberdomänen;

    Abstract : In the domain of cyber security, machine learning promises advanced threat detection. However, the volume of available unlabeled data poses challenges for efficient data management. This study investigates the potential for active learning, a subset of interactive machine learning, to reduce the effort required for manual data labelling. READ MORE

  3. 2. Exploring Advanced Clustering Techniques for Business Descriptions : A Comparative Study and Analysis of DBSCAN, K-Means, and Hierarchical Clustering

    University essay from Mittuniversitetet/Institutionen för data- och elektroteknik (2023-)

    Author : Wisam Orabi Alkhen; [2023]
    Keywords : Machine learning; Business descriptions; Search scope reduction; Relevant business terminology; Data analysis.;

    Abstract : In this study, we introduce several approaches to analyze large volumes of business descriptions by applying machine learning clustering and classification algorithms. The goal is to efficiently classify these descriptions, reducing the search scope and allowing for better business insights and decision-making processes. READ MORE

  4. 3. Self-learning for 3D segmentation of medical images from single and few-slice annotation

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Côme Lassarat; [2023]
    Keywords : Self-supervised Learning; Segmentation; Medical images; Självövervakad inlärning; segmentering; medicinska bilder;

    Abstract : Training deep-learning networks to segment a particular region of interest (ROI) in 3D medical acquisitions (also called volumes) usually requires annotating a lot of data upstream because of the predominant fully supervised nature of the existing stateof-the-art models. To alleviate this annotation burden for medical experts and the associated cost, leveraging self-learning models, whose strength lies in their ability to be trained with unlabeled data, is a natural and straightforward approach. READ MORE

  5. 4. Classification of Radar Emitters using Semi-Supervised Contrastive Learning

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Tim Jonsson; [2023]
    Keywords : ;

    Abstract : Radar is a commonly used radio equipment in military and civilian settings for discovering and locating foreign objects. In a military context, pilots being discovered by radar could have fatal consequences. READ MORE

  6. 5. Semi-Supervised Head Detection for Low Resolution Images

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Annie Biby Rapheal; [2023]
    Keywords : Object detection; Semi Supervised Learning; Head detection; Objektdetektion; Semisupervised Learning; Huvuddetektion;

    Abstract : Object detection is a widely researched and applied field in computer vision. Deep learning models have successfully been used for object detection over the years. The performance of State of the art (SOTA) object detection deep learning models is dependent on the number of labeled images. READ MORE