Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 25 for “"binary cross-entropy"”.

  1. Detection and localization of forgeries in digital images

    … of PADNET is tested using two loss functions, binary cross-entropy and weighted binary cross-entropy. Experimental results show that weighted binary cross-entropy is more efficient as a loss function for copy-move forgery while binary cross-entropy is more efficient for image splicing. In …

    uvic Repository record for Detection and localization of forgeries in digital images (opens in a new tab)

  2. Novel Instance-Level Weighted Loss Function for Imbalanced Learning

    Binary classification using imbalanced datasets remains a challenge. Typically, supervised learning algorithms minimize the binary cross-entropy objective function to determine the final parameter estimates. This objective function assumes an equal class distribution between the minority (i.e. …

    kennesaw Repository record for Novel Instance-Level Weighted Loss Function for Imbalanced Learning (opens in a new tab)

  3. Clinically-Inspired Hierarchical Classification of Chest X-rays with a Penalty-Based Loss Function

    … this, we developed a custom hierarchical binary cross-entropy (BCE) loss function that enforces label dependencies through fixed or data-driven penalty mechanisms. This approach aims to preserve diagnostic accuracy while producing structured and clinically coherent predictions. The …

    concordia Download PDF for Clinically-Inspired Hierarchical Classification of Chest X-rays with a Penalty-Based Loss Function (opens in a new tab)

  4. Deep learning for semantic segmentation of FIB-SEM volumetric image data

    … IoU in a mixed loss function with weighted Binary Cross-Entropy (wBCE) worked better than just binary cross-entropy, which is a standard loss function. The best performing architecture, in terms of both IoU score and predicted porosity was MultiResU-Net. MultiResU-Net had a test IoU of 70.5% …

    chalmers Repository record for Deep learning for semantic segmentation of FIB-SEM volumetric image data (opens in a new tab)

  5. An Exploration of the Word2vec Algorithm: Creating a Vector Representation of a Language Vocabulary that Encodes Meaning and Usage Patterns in the Vector Space Structure

    … algorithm: Huffman trees, neural networks, and binary cross-entropy. Chapter 4 provides a detailed discussion of the word2vec algorithm itself and includes a discussion of continuous bag of words, skip-gram, hierarchical softmax, and negative sampling. Finally, Chapter 5 explores some …

    unt Repository record for An Exploration of the Word2vec Algorithm: Creating a Vector Representation of a Language Vocabulary that Encodes Meaning and Usage Patterns in the Vector Space Structure (opens in a new tab)

  6. Detekce jógových pozic v obraze

    … 91% při použití aktivační funkce sigmoid a binary cross-entropy loss function. I přes slibně vypadající dosažené výsledky jsou hlavním přínosem této práce nástroje pro tvorbu datasetu a vytvořený Dataset samotný. Díky nim byla navrhovaná hypotéza úspěšně ověřena.

    brno-tech Repository record for Detekce jógových pozic v obraze (opens in a new tab)

  7. Finding a Viable Neural Network Architecture for Use with Upper Limb Prosthetics

    … architecture is a multi-entry categorical cross entropy convolutional neural network with 100% accuracy. The issue is that it is also the slowest method requiring 9 minutes to run. The next best method found was a single-entry binary cross entropy convolutional neural network, which was …

    kennesaw Repository record for Finding a Viable Neural Network Architecture for Use with Upper Limb Prosthetics (opens in a new tab)

  8. Learning-Based Guidance Map Generation for Heuristically Biased RRT Path Planning

    … is trained end-to-end using a combination of binary cross-entropy (BCE), dice, distance-transform, and continuity-based losses. Together, these losses encourage the guidance map to align with ground-truth paths, maintain spatial coherence, and reduce fragmentation without requiring explicit …

    buffalo Repository record for Learning-Based Guidance Map Generation for Heuristically Biased RRT Path Planning (opens in a new tab)

  9. Automatic Handwriting Analysis for Classifying Multi-Label Personality Traits using Transformer OCR

    … uses Focal Loss to handle class imbalance and Binary Cross-Entropy with Logits for accurate classification. The dataset includes 873 French and 181 English handwriting samples from CENPARMI, originally labeled for Extraversion and Conscientiousness. It has been expanded to cover all five BFFM …

    concordia Download PDF for Automatic Handwriting Analysis for Classifying Multi-Label Personality Traits using Transformer OCR (opens in a new tab)

  10. 3D Attention M-net for Short-axis Left Ventricular Myocardium Segmentation in Mice MR cardiac Images

    … loss term, besides general dice score loss and binary cross entropy loss, was also introduced to our hybrid loss functions to refine our segmentation contour. The proposed model outperforms previous generic models for segmentation, with similar number of parameters, in major segmentation metrics …

    jhu Repository record for 3D Attention M-net for Short-axis Left Ventricular Myocardium Segmentation in Mice MR cardiac Images (opens in a new tab)

  11. Outage performance and calibration of ML-assisted resource allocation for next-generation wireless systems

    … outperform those trained with conventional binary cross-entropy. The thesis further investigates the calibration of the ML-based outage predictor, evaluating the reliability of its probability estimates. Histogram-based reliability diagrams with logarithmic binning are proposed to better …

    qu-belfast Repository record for Outage performance and calibration of ML-assisted resource allocation for next-generation wireless systems (opens in a new tab) Embargoed until 2027-07-31

  12. Representation Learning for Texts and Graphs

    … with complete history. Moreover, weighting the binary cross-entropy loss function is crucial to mitigate the problem of class imbalance when detecting newly emerging classes. [...]

    cau-kiel Repository record for Representation Learning for Texts and Graphs (opens in a new tab)

  13. Testing Toxicity: Two Approaches to Toxicity Detection

    … was fine-tuned for 4 epochs using AdamW and binary cross-entropy loss. Comparing classifications (using thresholds of 0.12 for DistilBERT and 0.5 for Perspective API) revealed 40% agreement and a weak positive correlation (0.208) between outputs. Qualitative analysis showed DistilBERT to be …

    cuny-grad Repository record for Testing Toxicity: Two Approaches to Toxicity Detection (opens in a new tab)

  14. An integrated system for ultrasound-based surgical navigation of iliosacral screws

    … that deep ensembling used with versions of the binary cross entropy loss can significantly improve segmentation (mean Dice: 0.75) and calibration errors (mean expected calibration error: 0.24%). Third, we validated multiple graphical visualizations, and found that bullseye visualizations achieve …

    ubc Repository record for An integrated system for ultrasound-based surgical navigation of iliosacral screws (opens in a new tab) Download PDF for An integrated system for ultrasound-based surgical navigation of iliosacral screws (opens in a new tab)

  15. Modified Loss Functions for Algorithmic Bias Mitigation

    … Max Group Equity and Max Group Equality Binary Cross-Entropy (BCE). Both functions add the maximum group loss to the standard BCE loss and use a hyperparameter to adjust its significance. Max Group Equity BCE is more suited for unbiased data, while Max Group Equality BCE is useful for …

    mississippi Repository record for Modified Loss Functions for Algorithmic Bias Mitigation (opens in a new tab)

  16. Identifying Patients at Risk of Sudden Cardiac Arrest using Graph Representation Learning on Electronic Health Records

    … a graph regularization term is combined with binary cross-entropy loss to encourage similar visits to have closer learned representations. Because the graph is applied only during training, the final model is a standard LSTM with no additional graph operations, keeping prediction …

    calgary Repository record for Identifying Patients at Risk of Sudden Cardiac Arrest using Graph Representation Learning on Electronic Health Records (opens in a new tab)

  17. Banknote Authentication and Medical Image Diagnosis Using Feature Descriptors and Deep Learning Methods

    … is susceptible to error due to wide variations across interpreters, lethargy, and human subjectivity. Computer-aided diagnosis is vital to improvements in medical analysis, as they facilitate the identification of findings that need treatment and assist the expert’s workflow. Thus, this thesis is …

    concordia Download PDF for Banknote Authentication and Medical Image Diagnosis Using Feature Descriptors and Deep Learning Methods (opens in a new tab)

  18. Audio-Visual Feature Fusion through Transformers for Automated Depression Screening in Social Media Content

    … design a composite loss function that combines binary cross-entropy, focal loss, and L2 regularization to handle the noisy labels and class imbalance that are common in social media datasets. In the second part, we introduce MMFformer, a multimodal fusion transformer network that takes a …

    waterloo Repository record for Audio-Visual Feature Fusion through Transformers for Automated Depression Screening in Social Media Content (opens in a new tab)

  19. Few-shot learning for malware detection : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science at Massey University, Auckland, New Zealand

    … is optimized with the objection function of binary cross-entropy loss to improve detection accuracy. We then explored the specificity between malware in the presence of obfuscation techniques affecting the malware signature and proposed a novel Task-Aware Meta-Learning-based Siamese Neural …

    massey Repository record for Few-shot learning for malware detection : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science at Massey University, Auckland, New Zealand (opens in a new tab)

  20. LIVER SEGMENTATION AND LESION DETECTION IN MEDICAL IMAGES USING A DEEP LEARNING-BASED U-NET MODEL

    … incorporates both the Dice coefficient loss and binary cross-entropy loss. This combination effectively balances the trade-off between the accurate delineation of liver boundaries and maintaining the overall structure of liver tissue. Furthermore, we employ various data preprocessing techniques, …

    csusb Repository record for LIVER SEGMENTATION AND LESION DETECTION IN MEDICAL IMAGES USING A DEEP LEARNING-BASED U-NET MODEL (opens in a new tab)

Page 1 of 2