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 176 for “"Over-fitting"”.

  1. OVER-FITTING IN PROGRAM REPAIR AND SYNTHESIS

    … the auto-generated program can easily overfit the given examples. This thesis introduces a series of approaches to advance PbE techniques by alleviating the overfitting issues in program repair and synthesis. Our approaches are united by the idea of using program analysis to strengthen …

    nus Repository record for OVER-FITTING IN PROGRAM REPAIR AND SYNTHESIS (opens in a new tab) Download file for OVER-FITTING IN PROGRAM REPAIR AND SYNTHESIS (opens in a new tab)

  2. Investigation of over-fitting and optimism in prognostic models

    … the application of methods to reduce the risk of over-fitting. One method discussed in this work is the strategy proposed by Frank Harrell Jr. The various aspects of Harrell’s approach are discussed. An attempt is made to extend Harrell’s strategy to frailty models. Key issues such as missing data …

    birmingham Download PDF for Investigation of over-fitting and optimism in prognostic models (opens in a new tab)

  3. Evolutionary feature creation for ensembles

    … GP is used because it has the ability to discover underlying data relationships and express them mathematically (Kishore et al, 2000) establishing the structure and values of the solution (Guo et al., 2005). As the evolution progresses, GP discards the raw features that are not useful to solve …

    ets-quebec Download PDF for Evolutionary feature creation for ensembles (opens in a new tab)

  4. Improving plant disease recognition with generative adversarial network under limited training set

    … set. The issue of limited training data is overlooked. Thus, the over-fitting problem caused by a limited training set is discussed.</p> <p>Second, a new approach is proposed to solve the limited training set problem. The proposed method consists of four parts: CNN, data augmentation, GAN …

    iastate Repository record for Improving plant disease recognition with generative adversarial network under limited training set (opens in a new tab)

  5. A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing

    … training on limited data can easily lead to the over-fitting problem. To tackle these two issues, we introduce a novel dehazing network using the 2D discrete wavelet transform, namely DW-GAN. Specifically, we propose a two-branch network to deal with the aforementioned problems. By utilizing the …

    mcmaster Repository record for A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing (opens in a new tab)

  6. Study of non-rigid image registration algorithms

    … algorithms, and a special attention is given to over-fitting and under-fitting problems, which have identified as two major causes to limit accuracy of non-rigid image registration. In order to eliminate their impacts, two essential factors, leading to over-fitting and under-fitting, are …

    anu Repository record for Study of non-rigid image registration algorithms (opens in a new tab)

  7. EXPLAINABLE FEATURE- AND DECISION-LEVEL FUSION

    … of fusion. There is a great need to discover new theories to combine and analyze heterogeneous data arising from one or more sources. The work collected in this dissertation addresses the problem of feature- and decision-level fusion. Specifically, this work focuses on fuzzy choquet …

    mtu Repository record for EXPLAINABLE FEATURE- AND DECISION-LEVEL FUSION (opens in a new tab)

  8. Learning causal networks from gene expression data

    … introduce a learning algorithm which avoids the over-fitting tendencies of models with many parameters. We have validated the learning algorithm on simulated data, and carried out experiments on real microarray data. In doing so, we have discovered novel, yet plausible, biological relationships.

    unsw Repository record for Learning causal networks from gene expression data (opens in a new tab)

  9. Statistical Modelling of Markers of Severity in Rheumatoid Arthritis

    … dataset. A new method was developed to prevent over fitting of the PLS models which involved a three stage procedure. The first stage determined the order of predictive importance for the variables using 10 runs of 5, 7 or 10 fold cross validation (CV) (depending on the sample size). Absolute …

    whiterose Download PDF for Statistical Modelling of Markers of Severity in Rheumatoid Arthritis (opens in a new tab)

  10. Exploring machine learning design options in discourse parsing

    … the usefulness of different feature families and over-fitting. Consequently, we find out that the most effective feature sets for different tasks are different: part-of-speech (POS) and context features are the most effective for intra and multi-sentential structure prediction respectively, while …

    ubc Repository record for Exploring machine learning design options in discourse parsing (opens in a new tab) Download PDF for Exploring machine learning design options in discourse parsing (opens in a new tab)

  11. A STUDY OF NEURAL NETWORK APPLICATION IN BEATING STOCK INDICES

    … neural network is that it is more easy to reduce over-fitting and improve the performance on the test set. In this study, we focus on the application of neural networks in constructing portfolios of stocks which can outperform the stock index by a specified level. The results show that the deep …

    nus Repository record for A STUDY OF NEURAL NETWORK APPLICATION IN BEATING STOCK INDICES (opens in a new tab) Download file for A STUDY OF NEURAL NETWORK APPLICATION IN BEATING STOCK INDICES (opens in a new tab)

  12. Bayesian Hierarchical Models for Model Choice

    … only reduces model complexity, but also prevents over-fitting. From a Bayesian perspective, prior specification of model parameters plays an important role in model selection as well as parameter estimation, and often prevents over-fitting through shrinkage and model averaging.</p><p>We develop …

    duke Repository record for Bayesian Hierarchical Models for Model Choice (opens in a new tab)

  13. Early Stopping of a Neural Network via the Receiver Operating Curve.

    … error converge to zero which may give rise to over-fitting problems. To ensure that they do not over fit the training data and then fail to generalize well in new data, it appears effective to stop training as early as possible once getting AUC sufficiently large via integrating ROC/AUC …

    etsu Repository record for Early Stopping of a Neural Network via the Receiver Operating Curve. (opens in a new tab) Download PDF for Early Stopping of a Neural Network via the Receiver Operating Curve. (opens in a new tab)

  14. Comparison of algorithms for solving the least squares problem with applications in computed tomography

    … techniques and regularization in order to avoid over fitting. Multiple test problems are investigated using academic image phantoms from the literature as well as clinical image phantoms provided by the 3D Radiation Dosimetry Research Group. Comparison of the algorithms is done using performance …

    ubc Repository record for Comparison of algorithms for solving the least squares problem with applications in computed tomography (opens in a new tab) Download PDF for Comparison of algorithms for solving the least squares problem with applications in computed tomography (opens in a new tab)

  15. Data-driven data center traffic control

    … However, RL suffers from instability and over-fitting, deficiencies which so far render it unacceptable for use in DC networks. We analyze the requirements for data-driven policies to succeed in the DC context. And, we present a new emulator, Iroko, which supports different network …

    ubc Repository record for Data-driven data center traffic control (opens in a new tab) Download PDF for Data-driven data center traffic control (opens in a new tab)

  16. App Review Analysis via Active Learning: Reducing Supervision Effort Without Compromising Classification Accuracy

    … a high prediction accuracy and avoiding over-fitting. Given millions of reviews, preparing a training set is laborious.We propose to incorporate active learning, a machine learning paradigm,in order to reduce the human effort involved in app review analysis. Our app review classification …

    rit Repository record for App Review Analysis via Active Learning: Reducing Supervision Effort Without Compromising Classification Accuracy (opens in a new tab)

  17. Weakly Supervised Attention-Based Recognition Under Spectral, Turbulence, and Resource Variations

    … across diverse recognition systems, the risk of over-fitting and increasing bias have limited their applicability.This dissertation focuses on unsupervised learning—learning without precisely curated data—and argues that unsupervised learning methods can enable both discriminability and …

    nebraska Repository record for Weakly Supervised Attention-Based Recognition Under Spectral, Turbulence, and Resource Variations (opens in a new tab)

  18. Representing protein native states using weighted conformation ensembles

    … functioning of cellular processes cannot be overstated. To comprehensively understand their functional behaviors, structural models derived from experimental data have been developed and these models have played a significant role in explaining the functional mechanisms of proteins. The …

    iastate Repository record for Representing protein native states using weighted conformation ensembles (opens in a new tab)

  19. Intra and inter-brand calibration transfer for near infrared spectrometers

    … weakest methods, most likely due to a problem of over-fitting (specialization) of the calibration set. The transfer of calibrations across brands was possible with performances similar, or better, than in intra-brand calibration transfer.</p>

    iastate Repository record for Intra and inter-brand calibration transfer for near infrared spectrometers (opens in a new tab)

  20. Robust Deep Reinforcement Learning for Portfolio Management

    … may be susceptible to sampling errors and over-fitting and propose a robust deep reinforcement learning method that integrates techniques from reinforcement learning and robust optimization. We back-test and compare the performance of the developed algorithm, Robust DDPG, with UBAH (Uniform …

    ottawa-retro Repository record for Robust Deep Reinforcement Learning for Portfolio Management (opens in a new tab)

Page 1 of 9