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 84 for “"Learned Features"”.
-
A Smartwatch-Based Continuous Authentication System
… neural network to learn and extract features and one-class classifiers to classify authentication attempts as either legitimate or malicious. To the best of our knowledge, our work is the first to use learned features and one-class classifiers for continuous authentication with …
-
Towards Deep Learning for Long-term Visual Localization in Visual Teach and Repeat
… We improve on this work by learning visual features that can be used in the VT&R pipeline. With these deep learned features, we perform closed-loop path following across a full range of lighting change and also show that the learned features generalize to new areas. We further test the …
-
Generalizability of Representation Learning on Downstream Tasks
… theoretical generalizability of representations learned by contrastive learning by analyzing their performance in downstream linear regression tasks. To quantify the quality of these learned features, we provide rigorous proofs for the worst-case and expected downstream performances under …
-
Extraction and Interpretation of Deep Autoencoder-based Temporal Features from Wearables for Forecasting Personalized Mood, Health, and Stress
… neural network framework to automatically learn features from passively collected multi-modal sensor data. This process can be personalized by finetuning the general features with participant-specific data. Then, using the learned features, we performed personalized prediction of subjective …
-
Deep Neural Network Acoustic Models for ASR
… allow for better generalization of learned features to new situations, even when only small amounts of training data are available. In addition, DNN acoustic models scale well to large vocabulary tasks significantly improving upon the best previous systems. Different input feature …
-
Sparse feature learning for image analysis in segmentation, classification, and disease diagnosis.
… on intermediate data representation, called features that disentangle the hidden factors of variation in data. Moreover, machine learning models are required to be generalized, in order to reduce the specificity or bias toward the training dataset. Unsupervised feature learning is useful in …
-
Indoor Scene Localization to Fight Sex Trafficking in Hotels
… of matching approaches based both on hand-tuned features such as SIFT and learned features using state of the art deep learning approaches. We concentrate on spatio-temporal indexing of hotel rooms, and to date have an index of more than 1.5 million geo-coded images. Our smart-phone app collects …
-
Predicting parameters in deep learning
… learning models are over-parameterized and their learned features can be predicted given only a small fraction of their parameters. We then propose a method which exploits this fact during the training to reduce the number of parameters that need to be learned. Our method is orthogonal to the …
-
Evaluation of Convolutional Neural Networks Against Deepfakes Using Transfer Learning
… Transfer learning is a technique of applying the learned features by a network to a similar approach. It is employed to save time and resources in training, as it does not require a large dataset to allow the network to learn effectively. The Convolutional Neural Networks are tested against …
-
Learning Hierarchical Representations For Video Analysis Using Deep Learning
… deep models are three fold: 1) They learn the features directly from the raw signal in contrast to the hand-designed features. 2) The learning can be unsupervised, which is suitable for large data where labeling all the data is expensive and unpractical. 3) They learn a hierarchy of features …
-
Deep Neural Network Representations of Physiological Time-Series Sensor Data for Improved Recognition Performance
… classifiers utilizing both engineered and learned features. Additionally, a data fusion approach is proposed to handle multi-modal sensor data effectively. The overall objective of this work is to enhance the accuracy and utility of physiological sensor data in various applications, …
-
Novel feature construction technique for detecting anomalous faces and evaluating style transfer methods
… on how careful design and evaluation of deep-learned features are still necessary like hand-crafted features for computer vision tasks. We demonstrate this in two different domain problems – Anomaly Detection and Style Transfer. We present feature aggregation techniques and also quantitative …
-
Teisinių dokumentų skaitmeninė teksto analizė /
… and achieve faster training because of the learned features. For this purpose, a research is conducted about recurrent neural networks adaptation for solving problems with different lengths of input and output sequences. Also are reviewed: Vanishing gradient problem; Improvements on …
-
Quantifying Feature Overlaps in Deep Neural Networks and Their Applications in Unsupervised Learning and Generative Adversarial Networks
Deep neural network learn a wide range of features from the input data. These features take many different forms from, structural to textural, and can be very scale invariant. The complexity of these features also differs from layer to layer. Much like the human brain, this behavior in deep neural …
-
AUTOENCODER-ENHANCED CONVOLUTIONAL NEURAL NETWORKS FOR TARGET RECOGNITION IN SYNTHETIC APERTURE RADAR IMAGERY
… hindered by speckle noise that obscures target features. Traditional convolutional neural networks (CNN) achieve strong performance on clean images but degrade severely under noisy conditions, limiting their operational value. This thesis addresses this gap by introducing an …
-
Learning features for offline handwritten signature verification
… generation process, it is better to learn the features from data. As a first contribution, we propose a method to learn Writer-Independent features using a surrogate objective, followed by training Writer-Dependent classifiers using the learned features. Furthermore, we define an extension that …
-
Deep Learning for Enhancing Precision Medicine
… the practice, due to instability of selected or learned features derived from extremely high dimensional data with low sample sizes, which often results in overfitted models with high variance. To overcome the limitation of omics data, recent advances in deep learning models, including …
-
Improving neural language models on low-resource creole languages
… creole languages) can successfully transfer learned features during pretraining from a high-resource language to a low-resource creole language through a method called neural stacking. A method that normalized the vocabulary of a creole language to its lexifier also lowered perplexities of …
-
LOS/Multipath/NLOS Classifiers using Machine learning and Raytracing. A preliminary study to identify and address the Mulitpath error
… Autoencoder with a 1D-CNN layer to extract new features aimed at enhancing classification performance. By conducting three different simulations with varying data sorting methods, we demonstrate how sorting the data and the machine learning algorithm can influence the learned features which in …
Page 1 of 5