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 8 of 8 for “"Feature network"”.
-
Feature network methods for machine learning
We develop a graph structure for feature vectors in machine learning, which we denote as a feature network (FN); this is different from sample-based networks, in which nodes simply represent samples. FNs reveal the underlying relationship among feature vector components and re-represent features as …
-
Integrative analysis approaches for feature network and clustering for omics data
… of differential expression (DE) and differential network (DN) analysis between two distinct biological conditions using single type of ‘omic data, and (2) integration of multiple types of omics data, e.g. gene expression, microRNA, protein in order to determine the subtypes of disease. Although, …
-
The integration of seismic anisotropy and reservoir performance data for characterization of naturally fractured reservoirs using discrete feature network models
… This new method incorporates stochastic Discrete Feature Network (DFN) fracture modeling techniques, DFN model based fracture system hydraulic property and elastic anisotropy modeling, and non-linear inversion techniques, to achieve numerical integration of production data and seismic attributes …
-
Abstract representations in deep networks, capturing rapid and top-down cognitive processes in artificial learning
… is to allow general, re-usable learning based on features discovered from the environment. Recent advances in machine learning have provided a means for learning deep feature networks, in a manner that maintains analogies with human cognition. A range of important cognitive processes have been …
-
Machine learning on induced geometries
… the geometry of the dataset for efficient feature extraction. We produced induced geometry to allow for the use of these high performance methods on general datasets. The induced geometry is based on intrinsic measures from the feature network of the dataset. Convolutional neural networks …
-
Efficient video recognition with convolutional neural networks by exploiting temporal correlation in video data
… successful applications of convolutional neural networks (CNNs). However, applying deep CNNs to large numbers of video frames has recently emerged as a new challenge beyond image data due to the high computational requirements. Due to their similar appearances, CNNs often extract similar features …
-
Developing Generative Adversarial Networks for Classification and Clustering: Overcoming Class Imbalance and Catastrophic Forgetting
Generative adversarial networks (GAN) have attracted significant attention from the research community due to their superior clustering and classification abilities. However, data imbalance and continual learning settings cause poor GAN’s performance. In class imbalance problems, the thesis focuses …
-
Essays in Platform and Network Economics
… structure and pricing mechanics in marketsthat feature network economics and platform economics. The first chapter studies the network structure of small cell deployment within a city, by estimating and comparing the network effect of a carrier’s existing small cells and the competition effect …