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 153 for “"overfitting"”.
-
Word alignment and smoothing methods in statistical machine translation: Noise, prior knowledge and overfitting
This thesis discusses how to incorporate linguistic knowledge into an SMT system. Although one important category of linguistic knowledge is that obtained by a constituent / dependency parser, a POS / super tagger, and a morphological analyser, linguistic knowledge here includes larger domains than …
-
On boosting and noisy labels
… to its popularity is its resistance to overfitting. Previous experiments provide a margin-based explanation for this resistance to overfitting. In this thesis, the main finding is that boosting's resistance to overfitting can be understood in terms of how it handles noisy (mislabeled) …
-
Methodological advancements for improving performance and generating ensemble ecological niche models
… of occurrence data with the aim of reducing overfitting to sampling bias in ecological niche models (ENMs). Sampling bias in geographic space leads to localities that may also be biased in environmental space. If so, the model can overfit to those biases. As a preliminary test addressing this …
-
Model Selection with Information Criteria
… the criteria are consistent, underfitting, or overfitting. We further propose new model selection procedures to improve the information criteria. The procedures combine the information criteria with the probability of selecting a model and overfitting level, respectively. In addition, we …
-
Hyperparameter tuning and its effects on deep learning performance and generalization
… hyperparameter searches raise concerns about overfitting to re-used evaluation datasets. In this thesis, we perform a case study of hyperparameter search methods on SqueezeNet v1.0 with refinements added to the training procedure. We show that random search allows for improvement over baseline …
-
ASSET PRICING OPTIMIZATION THROUGH GENERATIVE ADVERSARIAL NETWORKS
… benefit of mitigating common challenges such as overfitting. This is an important finding, as it challenges the often-held belief that more complex, deeper models are invariably superior. Instead, we found that a simpler, less computationally intensive model can provide comparable results, and …
-
Tabular Machine Learning on Small-Size and High-Dimensional Data
… models, primarily due to the increased risk of overfitting arising from the curse of dimensionality and the limited data available to adequately represent the underlying distribution. Existing approaches often struggle to generalise effectively in such scenarios, resulting in suboptimal …
-
REGULARIZATION ON MACHINE LEARNING
… tool for machine learning problems. However, overfitting frequently occurs. To achieve better generalization, many regularization methods were proposed to reduce overfitting. In this thesis, we propose a simple-yet-effective regularization method called Drop-Activation. At the training phase, …
-
Acoustic-based machine learning diagnostic tool for voice disorders
… pathological speech data. However, it shows overfitting problem to some extent. This is a commonly seen problem due to the small data size. In order to address this issue, transfer learning with state-of-the-art CNN networks from image recognition field is applied in the pathological voice …
-
On improving the forecast accuracy of the hidden Markov model
… the parameterestimation method and, second, to overfitting caused by the large number of parameters that must be estimated. A general approach to forecasting is described which aims to resolve these two problems and so improve the forecast accuracy of the HMM. First, the application of extremum …
-
Evaluating Adaptive Layer Freezing through Hyperparameter Optimization for Enhanced Fine-Tuning Performance of Language Models
… fine-tuning on small datasets can lead to overfitting and a lack of generalization. Generalization is crucial when deploying models that perform a sensitive tasks in a real world environment, as it dictates how well it performs on unseen data. Conversely, overfitting is highly likely to …
-
Prognozavimo problemų tyrimas virtualioje akcijų viržoje /
… as usual. However, the recent publications on overfitting show that, under some unfavorable conditions, the correlation between the past and present results is negative. This work is to investigate both the influence of overfitting and the observed weak and, under some conditions, negative …
-
Investigation of prediction problems by the virtual stock exchange /
… as usual. However, the recent publications on overfitting show that, under some unfavorable conditions, the correlation between the past and present results is negative. This work is to investigate both the influence of overfitting and the observed weak and, under some conditions, negative …
-
Methods for imbalanced data in sports analytics: improving injury prediction models
… regularization with early stopping to control overfitting, alternative outcome-generation schemes for synthetic data, decision-rule restructuring through constructed risk-score ensembles, and incremental increases in injury prevalence to study how discrimination changes as the base rate shifts. …
-
Understanding Representations and Reducing their Redundancy in Deep Networks
… DeCov, which leads to significantly reduced overfitting (difference between train and val performance) and greater generalization, sometimes better than dropout and other times not. The regularizer is based on the cross-covariance of hidden representations and takes advantage of the intuition …
-
Deep Convolutional Neural Networks for Segmenting Unruptured Intracranial Aneurysms from 3D TOF-MRA Images
Despite facing technical issues (e.g., overfitting, vanishing and exploding gradients), deep neural networks have the potential to capture complex patterns in data. Understanding how depth impacts neural networks performance is vital to the advancement of novel deep learning architectures. By …
-
Deep Attentional Modulation for Zero-shot Learning in Object Recognition
… drops in the zero-and few-shot domains caused by overfitting. Most methods are focusing on learning a good, fixed feature extractor, then tying those features to new classes using linear transformations, which are less prone to overfitting on few examples. On the opposite side of this spectrum of …
-
The effect of the study region on GIS models of species geographic distributions and estimates of niche evolution; preliminary tests with montane rodents (genus Nephelomys) in Venezuela
… biotic interactions, this approach is prone to overfitting to conditions found near the known localities. In contrast, Method 2 is predicted to avoid such problems. I assessed differences in predictions for each species due to changes in the extent of the study region by calculating several …
-
Effects of acid hydrolysis conditions on cellulose nanocrystal yield and properties: A response surface methodology study
… ζ-potential of CNCs and yielded potentially data-overfitting regression models. With the BBD, the acid concentration significantly affected both the z-average diameter and Peak 1 value of CNCs. However, whereas the z-average diameter was more strongly affected by the hydrolysis temperature than …
-
Trainability and generalization of small-scale neural networks
… networks are considered to be less vulnerable to overfitting even with their overparameterized architecture, this project observed that properly trained small-scale networks indeed outperform its larger counterparts. The generalization ability of small-scale networks has been overlooked in many …
Page 1 of 8