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 505 for “"Loss Functions"”.
-
Exploring Loss Functions in Machine Learning
The loss function plays a critical role in machine learning. It is fundamental in training, evaluating, and optimizing machine learning models, directly impacting their effectiveness and efficiency in solving specific tasks. We explore three new loss functions and their applications. Softmax …
-
Generalized Loss Functions for Generative Adversarial Networks
… information-theoretic measures to generalize the loss functions of generative adversarial networks (GANs) under the objective of improving performance. A new generator loss function, called least kth-order GAN (LkGAN), is introduced, generalizing the least squares GANs (LSGANs) by using a kth …
-
Modified Loss Functions for Algorithmic Bias Mitigation
… impacted. This work studies using modified loss functions to mitigate race and sex bias caused by data and models. In the first experiment, the trade-off between fairness and accuracy when data is biased and unbiased is explored. A group risk function is introduced and used to create two …
-
Development of reservoir models using economic loss functions
… at each location by considering an economic loss function is demonstrated in this thesis. By applying a loss function that depicts the economic impact of an over or underestimation at a location and retrieving the optimal simulated value that minimizes the expected loss, a map of simulated …
-
Using Asymmetric Loss Functions in Time Series Econometrics
… the purpose of examining the role of asymmetric loss functions in time series analysis. Asymmetric loss functions can sometimes be interpreted as mathematical representations of risk-averse or risk-seeking behavior of economic agents. This thesis shows how these functions may be used for …
-
Designing Customized Loss Functions for Training Deep Neural Networks
This dissertation explores the critical role of loss functions in enhancing the predictive performance of deep machine learning models. Loss functions are an integral element of all the ongoing advances we witness daily in this domain. I design custom loss functions and their impacts on various …
-
Hyperbolic vision–language embeddings and loss functions for multimodal meme classification
… vanish. Under these conditions, angle-based losses saturate and performance collapses toward randomness. To address this, our main methodological contribution is a discriminative prototype loss (L_proto). Instead of classifying via token-likelihood, the model predicts labels by geodesic …
-
Studies on Dynamic Loss Functions and Curriculum Learning in OffensEval Datasets
… standards via curriculum learning and dynamic loss functions. By adapting a model to such data with the curriculum learning or dynamic loss functions, the systems are capable of scattering the focus properly on data of different difficulty levels. Experiments show both help the model learn …
-
Shrinkage estimators under generalized garrote and LINEX loss functions for regression analysis
… we explore the possibility of using different loss functions as the penalty in the non-negative garrote and develop the LINEX regression method as a novel shrinkage approach. We use a numerical optimization technique to estimate the LINEX regression coefficients. In addition, through simulation …
-
Designing Loss Functions for Learning Sound Timbre Audio Representations in Variational Autoencoders
… study investigates the effect of audio-related loss functions, audio feature extraction methods, and the addition of a synthesis layer on the reconstruction quality and latent space organization of variational autoencoders (VAEs). Three different experiments were conducted to address these …
-
Applications of Novel Loss Functions and Interpretable Machine Learning for Clinical Risk Prediction
… as data pre-processing, an appropriate model and loss (cost) function, imputation of missing values, assessment of discriminatory power and probability calibration, interpretability or explainability methods, and selection of a decision threshold. Although statistical models (such as logistic …
-
Generative Adversarial Networks Based on a General Parameterized Family of Generator Loss Functions
… introduces a unifying parameterized generator loss function for generative adversarial networks (GANs). We establish an equilibrium theorem for our resulting GAN system under a canonical discriminator in terms of the so-called Jensen-$f$-divergence, a natural generalization of the …
-
Asymmetric Loss Functions and Combination of Forecasts with Applications in Equity Premium Prediction
… methods, called the Discount Asymmetric Square Loss Function (DASLF), the Discount Linex Loss Function (DLLF), the Discount Lin-Lin Loss Function (DLLLF) and the Discount General Entropy Loss Function (DGELF) are proposed to maximize forecast accuracy and boost the efficiency of forecasts …
-
Investigating Deep Learning for Low-Quality MRI Enhancement: From Loss Functions to Temporal Modeling
… technical assessment of model design choices, loss functions, and contextual integration. The first direction examines the role of adversarial loss in medical image enhancement. While adversarial components are frequently incorporated into hybrid loss functions alongside pixel- and …
-
Analysis of loss functions in XVAE-GAN: A novel two-view image generation network
DSpace SAF Submission Ingestion Package generated from Vireo submission #14457 on 2020-02-28 at 17:35:35
-
Towards Precise Localization in Object Detection: Stable Matching Strategies and Advanced Bounding Box Regression Loss Functions in Deep Neural Networks
… in detection models. Bounding box regression loss functions play a pivotal role in object localiza- tion by refining predicted bounding boxes to achieve accurate alignment with ground truth boundaries. In gradient-based learning, these loss functions guide the optimization process, enhancing …
-
From diversity to adaptivity : effective multitask learning and continual learning neural architectures
… optimizing a linear combination of multiple loss functions and enabling continual learning for deep neural networks. The first part of the thesis addresses the challenge of optimizing loss functions composed of heavily conflicting components. In deep learning, it is common practice to …
-
Elite-driven support vector machines for classification
… as support vectors, determined by the choice of loss functions. Each loss function results in a specific decision boundary and identifies a unique set of support vectors, leading to varied classification performances. This thesis proposes a novel SVM methodology that gives additional weight to a …
-
Improving deep learning through loss-function evolution
… dissertation tackles a new type of metalearning: loss-function optimization. Loss functions define a model's core training objective and thus present a clear opportunity. Two techniques, GLO and TaylorGLO, were developed to tackle this metalearning problem using genetic programming and …
-
Analysis of loss function for binary classification problem in deep learning /
… the applicability of different deep learning loss functions for binary classification problems. Misclassification error-rate based generic loss functions are not directly adapted for optimization of binary classification specific metrics. Consequently, different binary classification problems …
Page 1 of 26