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 43 for “"hyper parameters"”.
-
Impact of the Choice of Hyper-parameters on Statistical Inference using SGD Estimates and Optimal Experimental Designs for Precision Medicine with Multi-component Treatments.
North Carolina State University Theses Statistics.
-
Distributed autonomous intersection management with neuro-evolution
… task. In particular we investigate three key hyper-parameters: Neuro-Evolution algorithm, task difficulty and problem exposure. A traffic simulator was developed and the hyper-parameters were used to evolve car controllers, which where then tested on unseen tasks. We show that certain key …
-
A Prediction Modeling Framework For Noisy Welding Quality Data
… prediction accuracy on such noisy data. Optimal hyper-parameters for SVR are selected by particle swarm optimization (PSO) with meta-modeling. Constructing bagging models require</p> <p>114</p> <p>more computational costs than a single model. Also, evolutionary computation algorithms, such as …
-
Meta-level learning for the effective reduction of model search space.
… for less complex tasks that require thousands of parameters to learn. However, the state-of-the-art models, e.g. deep learning models, require well-tuned hyper-parameters to learn millions of parameters which demand specialized skills and numerous computationally expensive and time-consuming …
-
Models for Pedestrian Trajectory Prediction and Navigation in Dynamic Environments
… thesis extends and modifies that model to output parameters for a multimodal distribution, which better captures the uncertainty inherent in pedestrian movements. Additionally, four novel architectures for representing neighboring pedestrians are proposed; these models are more general than …
-
Random Projection Optimal Trees Ensemble
… when used with the wrong choice of their hyper-parameters values and/or when there are noisy features in the data. Thus, feature selection and fine tuning hyper-parameter could improve predictive accuracy of ensemble classifiers. This thesis first investigates the effect of feature …
-
Deep learning for supernovae detection
… Convolutional Neural networks are trained and hyper-parameters tuned to outperform previous approaches and find that human labelling errors are the primary obstacle to further improvement. The tuning and optimisation of the deep models took in excess of 700 hours on a 4-Titan X GPU cluster.
-
Understanding Adversarial Training: Improve Image Recognition Accuracy of Convolution Neural Network
… neural network; single layer, defined hyper-parameters in Keras, then train and test by the datasets and computed accuracy and loss of recognition. Second, I modify the network to adjust a network structure and hyper–parameters one by one, then compare to the basic network. Next, I …
-
Representation learning in multi-dimensional clinical timeseries for risk and event prediction
… Multi-task Gaussian Process (MTGP) hyper-parameters as latent features to estimate correlations within and between signals in sparse, heterogeneous time series data. We evaluate the hyper-parameters for forecasting missing signals in traumatic brain injury patients, and predicting …
-
Hyperparameter Optimization of Opaque Models for Autonomous Vehicle Algorithms
Algorithms usually consist of many hyperparameters that need to be tuned to perform efficiently. It may be possible to tune a handful of parameters manually for simple algorithms however as the algorithm becomes more complex the number of hyper- parameters also increases which makes finding the …
-
Market state discovery
… ASPC does not rely on the art of selecting good hyper-parameters such as, the number of states a priori. ICC's utility as a market state discovery algorithm is limited.
-
The Low-rank Simplicity Bias in Deep Networks
… and after training and is resilient to hyper-parameters and learning methods. We further demonstrate how linear over-parameterization of deep non-linear models can be used to induce low-rank bias, improving generalization performance on CIFAR and ImageNet without changing the modeling …
-
Evolutionary deep learning
… are exhibiting an explosion in the number of parameters that need to be trained, as well as the number of permutations of possible network architectures and hyper-parameters. There is little guidance on how to choose these and brute-force experimentation is prohibitively time consuming. We …
-
Real-Time Motion Prediction for Efficient Human-Robot Collaboration
… or use regression models offline to fit hyper-parameters in the hope of capturing a model encompassing human motion. While these methods provide good initial results, they are missing out on leveraging well-studied human body kinematic models as well as body and scene constraints which …
-
A flexible framework for composing end to end machine learning pipelines
… a pipeline is specified, a user can tune its hyper-parameters, as well as fit and predictions, with minimal code. When building MLBlocks, we first develop a data science block library that seamlessly integrates third party blocks without integration code, providing a foundation for users to …
-
Short-term traffic forecasting for a smart satellite communications system
… and executing changes to the satellite's parameters. As the system's cycle time grows the user's desired data rate changes causing an optimized solution based on an erroneous traffic model. This thesis proposes a comparison of single user models using a gradient boosting algorithm, and a …
-
Bias and Fairness of Evasion Attacks in Image Perturbation
… stands, the Fawkes system has a fixed set of hyper parameters for amount of perturbations added per image, which essentially means that they consider all users be treated identically in terms of amount of perturbations added. However, from testing our hypothesis through running various …
-
A Bi-Encoder LSTM Model for Learning Unstructured Dialogs
… by using several similarity functions, model hyper-parameters and word embeddings on the proposed architecture.</p>
-
Fault detection in manufacturing equipment using unsupervised deep learning
… across applications without changes to the hyper-parameters or architecture. Previous work has demonstrated the efficacy of autoencoders in unsupervised anomaly detection systems. In this work we propose a novel variant of the deep auto-encoding Gaussian mixture model, optimized for time …
-
Machine Learning Based Prediction of Reinforced Concrete Members’ Shear Friction Capacity
… capacity. To achieve optimal accuracy, the hyper parameters of each model have been appropriately tuned. Several statistical metrics were used to evaluate the performance of the proposed models. A comparison with the ACI318 (2019), AASHTO (2012), CSA A23.3 (2019), and an empirical equation …
Page 1 of 3