ASU Electronic Theses and Dissertations
This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
Filtering by
- All Subjects: Business Administration
- All Subjects: deep learning
The eld has seen tremendous success in designing learning systems with hand-crafted
features and in using representation learning to extract better features. In this dissertation
some novel approaches to representation learning and task learning are studied.
Multiple-instance learning which is generalization of supervised learning, is one
example of task learning that is discussed. In particular, a novel non-parametric k-
NN-based multiple-instance learning is proposed, which is shown to outperform other
existing approaches. This solution is applied to a diabetic retinopathy pathology
detection problem eectively.
In cases of representation learning, generality of neural features are investigated
rst. This investigation leads to some critical understanding and results in feature
generality among datasets. The possibility of learning from a mentor network instead
of from labels is then investigated. Distillation of dark knowledge is used to eciently
mentor a small network from a pre-trained large mentor network. These studies help
in understanding representation learning with smaller and compressed networks.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
The first chapter analyzes the background, theatrical and particle reasons of this research. The author argues that the management of law firm needs a set of good system. The first one is operating the law firm in scale, and the other on is corporate management model, which shall be constructed in detail in the paper and will be put into practice by the law firm in which the author is worked.
The second chapter will introduce modern management theory, combining the situation of management in our law firm to analyze, raising some reasonable suggestions and instructions to promote our law firm to achieve the corporate management.
In the third chapter, the first chapter, starting with the review of the development process of foreign and our law firms, listing the organizational forms and the characteristics of our law firm, analyzing the situation and the drawbacks of the law firm management.
The fourth and fifth chapter introduce he background, the connotation of the corporate management model, listing the development and successful experience of some typical cases in respect of corporate management.
In the last chapter, the construction of corporate management model will be introduced in terms of organization form, human resource management and informationizing development.
The corporate management model is not mature in china. Though it is not easy to reform the existing model, but it should be believed that the development benefiting the legal industry will be achieved.
text, etc. into feature representations that are convenient for computational process-
ing. Deep neural networks have proven to be very efficient feature extractors for a
variety of machine learning tasks. Generative models based on deep neural networks
introduce constraints on the feature space to learn transferable and disentangled rep-
resentations. Transferable feature representations help in training machine learning
models that are robust across different distributions of data. For example, with the
application of transferable features in domain adaptation, models trained on a source
distribution can be applied to a data from a target distribution even though the dis-
tributions may be different. In style transfer and image-to-image translation, disen-
tangled representations allow for the separation of style and content when translating
images.
This thesis examines learning transferable data representations in novel deep gen-
erative models. The Semi-Supervised Adversarial Translator (SAT) utilizes adversar-
ial methods and cross-domain weight sharing in a neural network to extract trans-
ferable representations. These transferable interpretations can then be decoded into
the original image or a similar image in another domain. The Explicit Disentangling
Network (EDN) utilizes generative methods to disentangle images into their core at-
tributes and then segments sets of related attributes. The EDN can separate these
attributes by controlling the ow of information using a novel combination of losses
and network architecture. This separation of attributes allows precise modi_cations
to speci_c components of the data representation, boosting the performance of ma-
chine learning tasks. The effectiveness of these models is evaluated across domain
adaptation, style transfer, and image-to-image translation tasks.
The rapid development of mobile Internet, highly transparent information, consumers grasp the sovereignty, along with the rise of the middle class, consumption increase encouraged personalized, customized needs. The boundaries between online and offline are becoming increasingly blurred. Consumers are more inclined to choose multi-category with service channel providers. If the retailers still rely on good market resources, and the difference between the sales and purchase of commodities, they will face a huge challenge of the decrease in passenger flow and a decline in performance.
The paper takes the relationship between maternal-baby nursing retailers and targets customers as the study object, based on customer service of maternal-baby nursing retailer data, empirical studies, we found that this particular group, mothers and babies, especially value safety, quality, public praise and community review. If the retail enterprise attaches importance to establishing relationships with customers and enhances the relational viscosity through mutual trust, emotional formation and spread of public praise, it will help to increase the traffic volume and increase the output value of single customers.
The maternal-baby nursing retailers form a strong relationship between enterprises and customers by establishing a strong relationship between products and customers, employees and customers, and customers to customers. Maternal-baby nursing retailers operate single-customer value deeply, build a heavy membership system and manage customer assets, thereby enhancing their brand and performance.
The research on the method of establishing the strong tie can be considered as an analysis of feasibility. The research results of this paper will help to improve the overall customer service experience and satisfaction of the mother and infant retail industry, enhance the development of the whole industry and draw significance lessons from other service industries.
Despite the increased importance of services in the manufacturing sector, the academic literature is yet to investigate the many questions that arise under this new manufacturing paradigm. Perhaps for the same reason study of servitization is listed as a research priority in recent publications both in the field of service operations management and in the field services marketing. This dissertation covers three essays aimed at disentangling multiple aspects of the role of services in the manufacturing sector. The literature on the drivers and implications of transition towards services in manufacturing firms is limited. The three studies in this dissertation aim at shedding light on this issue.
Specifically, the first essay looks at the innovation benefits of service transactions with customers. This paper demonstrate the value of services in getting manufacturers closer to customers and allowing them glean useful information from their service interactions. The second essay investigates the antecedents of service strategy adoption. We suggest that the extant diversification theory does not fully explain servitization and this phenomenon represents a unique type of diversification, which is likely driven by different factors. Through econometric analysis of financial data over a 27-year period, this study explores characteristics of product, firm resources, competition, and industry that encourage adoption of service strategies in manufacturing sector. Finally, the third essay takes a deeper dive and focuses on dealerships, as service centers, in the automobile industry. It investigates the role of dealerships in the success of automakers and explores dealership traits that are critical for market success of an automobile brand.