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 239 for “"Hyperparameter Tuning"”.
-
Practical Bayesian optimisation for hyperparameter tuning
… high-level properties, also known as the model’s hyperparameters. Examples include the architecture of a neural network, the class and parameters of a stochastic optimisation algorithm, the number of trees in a random forest or the kernel in a Gaussian process. One of the key challenges in …
-
Practical Bayesian optimisation for hyperparameter tuning
… high-level properties, also known as the model’s hyperparameters. Examples include the architecture of a neural network, the class and parameters of a stochastic optimisation algorithm, the number of trees in a random forest or the kernel in a Gaussian process. One of the key challenges in …
-
Hyperparameter tuning of StyleGAN2 on bridge inspection images
… of GAN architectures, to tackle data limitation. Hyperparameter tuning is applied to optimize StyleGAN2 to produce high-quality images. The models were trained with transfer learning and data augmentation, and were evaluated using Fréchet Inception Distance (FID) and Kernel Inception Distance …
-
Machine learning hyperparameter tuning via Bayesian optimization exploiting monotonicity
… The motivating problem is optimization of hyperparameters of machine learning algorithms where we argue that the objective, validation error, can be decomposed into two approximately monotonic functions of the hyperparameters, along with some theoretical justification. Our proposed …
-
Scalable Gaussian Processes and Bayesian Optimization with Application to Hyperparameter Tuning
… with an emphasis on its application in hyperparameter tuning. By leveraging the probabilistic modeling strengths of GPs, BO can efficiently traverse the hyperparameter space, thus reducing the need for extensive model evaluations. Through the introduction of novel algorithms and …
-
Hyperparameter tuning and its effects on deep learning performance and generalization
Hyperparameter tuning is an integral part of deep learning research. Finding hyperparameter values that effectively leverage the strengths of network architectures and training procedures is crucial to maximizing performance. However, extensive hyperparameter searches raise concerns about …
-
Solution Path Algorithms for Distributionally Robust Regression and Classification
… machine learning models. The regularization hyperparameters control the bias-variance trade-off and will influence the generalization performance. However, existing works mainly focus on modeling part and solve the model by off-the-shelf solvers. To perform the hyperparameter tuning, we need …
-
Topics in Differential Privacy
… analytical nature. The second challenge concerns hyperparameter tuning with DP algorithms. Practitioners often overlook privacy leaks resulting from hyperparameter tuning, despite evidence demonstrating that hyperparameter choices can reveal private information about the underlying dataset. We …
-
Optuna Hyperparameters Optimization for Discriminating Life-Threatening Ventricular Arrhythmia Problem
In the realm of machine learning, efficient hyperparameter tuning is critical for improving model performance. This thesis investigates automated hyperparameter optimization, focusing on the Optuna framework. Various optimization techniques and Optuna's key characteristics are introduced, followed …
-
Improving the ML Tradeoff Curve: Efficiencies in Computation, Memory, and Tuning
… model capability. More training iterations, hyperparameter tuning, model parameters, or data are generally beneficial. For a computational or memory resource, and a capability metric, there is a a Pareto frontier. Navigating this tradeoff curve, i.e. scaling resources to scale model …
-
Hibridinių mašininio mokymo metodų taikymas sistemų įsilaužimų aptikimui /
… optimisation significantly improved the results. Hyperparameter tuning increased the attack recall rate, with the (DAE+XGB) model achieving a 64.0% recall rate. In further experiments, embedding fusion was performed by com‑ bining the features extracted by both autoencoders, resulting in the best …
-
Clinical Validation Of Tabpfn-2.5: Zero-Shot Performance, Data-Scarce Robustness, And Distilled Models For Real-Time Clinical Decision Support
… by complex development processes, the need for hyperparameter tuning, and variability in performance across datasets. These challenges are especially relevant in data-scarce clinical settings. This thesis evaluates TabPFN-2.5, a transformer-based tabular foundation model designed to perform …
-
Enhancing Surgical Gesture Recognition Using Bidirectional LSTM and Evolutionary Computation: A Machine Learning Approach to Improving Robotic-Assisted Surgery
… employs evolutionary computation techniques for hyperparameter tuning, systematically searching for optimal configurations to enhance model performance. The evaluation metrics include training and validation loss, accuracy, confusion matrices, prediction time, and model size. The results …
-
Statistical Methods for Neural Networks
… fit. In Chapter 4, we develop an algorithm for hyperparameter tuning in neural networks that does not require validation data. Leveraging information from the partial derivative function of the network output with respect to network inputs, we offer an alternative to standard hyperparameter …
-
Mikroplastiko dalelių segmentacija mikroskopiniuose vaizduose /
… on an FTMC image set. Data augmentation and hyperparameter tuning enabled the model to identify most particles accurately. Although background artefacts and limited training data still constrain performance, the study shows that UNet is suitable for microplastics particle search in …
-
Adaptive traffic signal control using deep reinforcement learning for network traffic incidents
… implemented to solve the limitations of DQN. Hyperparameter tuning was conducted to find the best parameter combination for the training process, and the results showed that DQN outperformed other controllers in terms of the system-wise and intersection-wise queue distribution and vehicle …
-
Meta-optimization in safe reinforcement learning: Enhancing safety at training and deployment with fewer hyperparameters
… challenges such as sample efficiency and hyperparameter tuning hinders its applicability in real-world scenarios. To address these challenges, this thesis proposes various approaches. First, a metagradient-based training pipeline called Meta Soft Actor-Critic Lagrangian (Meta SAC-Lag) is …
-
Improving Bayesian Optimization for Machine Learning using Expert Priors
… relies on the proper setting of numerous hyperparameters. Manual tuning by an expert researcher has been a traditionally effective approach, however it is becoming increasingly infeasible as models become more complex and machine learning systems become further embedded within larger …
Page 1 of 12