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 50 for “"hyperparameter tuning"”.
-
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 …
-
Map Inference from Satellite Segmentation Data through Reinforcement Learning: A Novel Approach
… algorithms use supervised learning and require hyperparameter tuning on a given location to be able to infer maps with high accuracy. In addition, these algorithms are trained for metrics like per-pixel loss but not trained on end-to-end objectives. In this project, we experiment with a …
-
Optimising the Optimiser: Meta NeuroEvolution for Artificial Intelligence Problems
… fully solve a task in order to evaluate a set of hyperparameter values, conventional hyperparameter tuning methods can be highly sample inefficient and computationally expensive. Many widely used reinforcement learning architectures originate from scientific papers which include optimal …
-
Distributed estimation algorithms for autonomous systems
… objective constraint at the same time. Hyperparameter tuning techniques for multiple algorithms preventing RMSE drift and communication network inefficient usage are described. An example of distributed algorithm application with rovers shows the power of such algorithms in robotics.
-
Automated test case prioritization using machine learning for large scale continuous integration environments
… of feature extraction and selection, ML model tuning, and evaluation in large-scale CI environments. This thesis aims to integrate ML techniques to improve the prioritization process in large-scale CI systems. The core contribution is automating the selection of relevant features and tuning ML …
-
Relative Position Control for Satellite Formation Flying
… along-track separations, but required proper hyperparameter tuning. A novel hyperparameter tuning strategy was developed using Bayesian optimisation to improve controller performance. Seven hyperparameters were tuned using a unique algorithm that penalised satellite crashes and rewarded …
-
Deep learning methods for large-scale physics
… problems in physics (1) that require significant hyperparameter tuning and (2) for which traditional techniques are computationally prohibitive. To this end, this thesis addresses these problems by drawing on connections between different branches of mathematics, optimization, statistics, and …
-
Application of CNN-gcForestCS to cassava leaf image classification
… capabilities. However, CNNs require complex hyperparameter tuning and can be computationally intensive to train. GcForestCS (multi-grained cascade forest with confidence screening) presents an alternative statistical learning method that can be trained using CPU, and requires less complex …
-
What drives the differences between transaction and offered prices on the real estate market in Prague?
… After thorough architecture adjustment and hyperparameter tuning, we propose a model which is able to improve the current best prediction on the dataset by more than 12 %.
-
Analyzing Multi-Agent Reinforcement Learning and Coevolution in Cybersecurity Simulations
… demonstrate a greater degree of robustness to hyperparameter misspecification in this environment. Our results suggest that coevolution may prove to be a satisfactory benchmark for hyperparameter tuning of adversarially trained reinforcement learning agents in the absence of other metrics for …
-
Explicit Regularization for Overparameterized Models
… and is sensitive to the choice of regularization hyperparameter. To this end, we propose a new approach to optimize objectives with explicit regularization, called Regularizer Mirror Descent (RMD). In the overparameterized regime, where the number of model parameters exceeds the size of data, RMD …
-
Mixed-Variable Bayesian Optimization using Prior-Data Fitted Networks
… as materials science, engineering design, and hyperparameter tuning. Traditional BO relies on Gaussian processes (GPs) as surrogate models, but GPs face limitations in flexibility and scalability. Prior-Data Fitted Networks (PFNs) have recently emerged as a promising alternative, leveraging …
-
Democratizing data science through interactive curation of ML pipelines
… only attainable via mindful data preprocessing, hyperparameter tuning and model selection. Domain experts are often overwhelmed by such complexity, de-facto inhibiting a wider adoption of ML techniques in other fields. Existing libraries that claim to solve this problem, still require …
-
Deep learning-based seagrass detection and classification from underwater digital images
… requires architectural engineering and hyperparameter tuning. This thesis investigates the effective development of CNNs on multi-species seagrass datasets to minimise the requirement of architectural engineering and manual hyperparameter tuning for CNN models. This thesis develops a …
-
Development of an Emotion Recognition Classifier from Body Language Using Deep Learning for the Children with Autism to Help Identifying Human Emotions
… is essential for analyzing video data. Same hyperparameters from CNN+RNN were used to train the CNN+LSTM model due to limited time and limited computation resources. For this experiment, CNN+RNN outperforms the CNN+LSTM with a 12.33% higher test accuracy for the combined video datasets. …
-
Classification of computer programs in the Scratch online community
… "game", and "other". After an extensive hyperparameter tuning process, I am able to train a classifier model with an F1 Score of 0.737. I include in this paper an in-depth analysis of the unsupervised and supervised models, and explore the different elements that were learned during …
-
Empirical Approaches to Challenges in Neural Network Training and Deployment
… they can approximate with a practical amount of hyperparameter tuning, which contrasts with conventional wisdom that adaptive methods generalize worse than non-adaptive methods. We next focus on multi-task learning, and show that using a particular ordering of training data can improve …
-
Benchmarking Graph Transformers Toward Scalability for Large Graphs
… Spectral Attention Network (SAN) and performing hyperparameter tuning, we built a GT architecture that performs comparably to GraphGPS on the node classification task on the Cora and CiteSeer datasets. Compared to the modified version of SAN that we started with, our architecture is faster to …
-
Antimicrobial Peptides Activity and Efficacy Prediction by Stochastic Models and Machine Learning Methods
… This model produced decent accuracy with manual hyperparameter tuning, and the results can be applied to engineer better AMPs.
-
Geometric Dimensionality Reduction
… Neighbor Embedding) suffer from irreversibility, hyperparameter tuning sensitivity, and computationally costly internal processes. Even LLE (Local Linear Embedding), which is designed to reduce the embedding dimension of intrinsically lower dimensional data, is sensitive to noise & variance due to …
Page 1 of 3