Matching Items (125)
Filtering by
- Creators: Yang, Yezhou
- Member of: ASU Electronic Theses and Dissertations
Description
En el siglo XXI nuestra vida se está cruzando constantemente con la tecnología, tanto que algunos declaran que nuestro mundo se ha hecho posthumano, ya que no se puede separar al ser humano de la máquina. Aunque algunos se sientan amenazados por estas tecnologías, otros están abrazando la Red Mundial, aprovechándose de las infinitas oportunidades que ofrece. Uno de estos elementos fundamentales que internet posibilita es la capacidad de comunicarse directamente con otras personas. El blog por ejemplo, o bitácora en español, permite que los usuarios se proyecten a sí mismos o a sus pseudo-identidades, sus pensamientos e ideas a través del texto que escriben en internet. También sus lectores pueden responder a estos autores inmediatamente. Los posts publicados--entradas en una página web--, aunque aparecen cronológicamente, son episodios fragmentados. Pero el blog no se limita a la producción de un texto sino que el autor puede también "jugar" con el cuerpo del texto para añadir hipervínculos y multimedia. Esta forma de escribir está cambiando lo que se considera "válido" como texto, incluso lo que se considera literatura. El objetivo de este trabajo no es estudiar la literatura digital en su totalidad, sino específicamente en algunas obras escritas por mujeres en internet. Si se considera la escritura digital como una forma de arte marginalizada, se podría decir que la escritura realizada por mujeres en internet experimenta una doble-marginalidad debido al hecho de que la literatura de mujeres siempre ha sido marginal al canon. Este estudio tomará un punto de vista transatlántico, incluyendo en el mismo a varias escritoras hispanohablantes de diferentes edades, experiencias y con variados motivos en su trabajo que publican sus obras en internet. Estas autoras incluyen las blogueras Almudena Montero (española) yMaría Amelia López Soliño (española); la periodista ciudadana Yoanis Sánchez (cubana); y la poeta digital/crítica Belén Gache (española-argentina). En esta tesis he explorado y considerado la noción de que el internet sirve como un medio de democratización puesto que, hasta cierto punto, las fronteras de género y nacionalidad desaparecen. Por esta razón, este trabajo va a considerar varias teorías tales como el postmodernismo, las teorías sobre la escritura de mujeres y teorías sobre la democratización de la tecnología para analizar la literatura que se encuentra en la red. Aunque las escritoras analizadas en este proyecto son distintas, y usan la tecnología de maneras diferentes, tienen una misma meta: expresarse libremente y comunicarse directamente con sus lectores al conectarse a internet. Mi hipótesis de trabajo consiste en que estas mujeres escriben de una manera particular--es decir, que no escriben igual a los hombres que escriben en internet--y que la red ofrece una plataforma única a las mujeres: en este espacio ellas son más activas--en oposición a la literatura tradicional-- en cuanto a compartir y publicar su propio trabajo e ideas.
ContributorsByron, Jennifer E. (Author) / Urioste-Azcorra, Carmen (Thesis advisor) / Tompkins, Cynthia (Committee member) / García-Fernández, Carlos Javier (Committee member) / Arizona State University (Publisher)
Created2013
Description
The subject of this study is the work of Spanish novelist J. Á. González Sainz, comprised of Los encuentros (1989), Un mundo exasperado (1995), Volver al mundo (2003) y Ojos que no ven (2010). His work, which is structurally demanding, treats themes such as morality, terrorism, the nostos or return to one's homeland, and nature. He has been connected to the "dehumanized novel" of Juan Benet, though his career demonstrates an attempt to make clear references to historical reality. González Sainz has acquired a measure of prestige in the estimation of important critics. With his latest book, he has furthermore gained recognition for his moral commitment in opposing the terrorism of ETA, and his work has entered debates on current events. In my study I argue that this formally rigorous narrative has a singular capacity for political engagement. I argue that González Sainz is an example of the integration of ethics in a narrative discourse whose semantic density allows a commitment with moral conflicts. To situate it in the context of contemporary Spanish fiction, I relate Pierre Bourdieu's notion of the literary field to the proposals concerning the history of literature of Pablo Gil Casado, Gonzalo Sobejano, Ramón Buckley, Ignacio Soldevila Durante and others. I follow three lines of investigation: terrorism in literature; ethics; and the political engagement of the writer. Ethics, whose relation to literature has been studied by Zachary Newton, Wolfgang Hallet or Nina Rosenstand, has allowed the author a political engagement in opposition to terrorism in general and in particular in opposition to ETA. González Sainz exhibits an equilibrium between aesthetic and ethical values of literature. In the plural context of the latest fiction in Spain, his novels have found a place in the tradition that since the middle of the twentieth century has been characterized by a dialectic between political engagement and the autonomy of literature. The theme of ETA terrorism and his structural rigor situate González Sainz's work in a position that maintains the validity of this dialectic.
ContributorsMartín de Marcos, Gonzalo (Author) / García-Fernández, Carlos Javier (Thesis advisor) / Volek, Emil (Committee member) / Acereda, Alberto (Committee member) / Arizona State University (Publisher)
Created2012
Description
Este trabajo examina la producción literaria y cultural chicana/méxicosudoesteña de las distintas épocas coloniales del sudoeste: la época colonial española (1521-1821), la época colonial angloamericana (1848-1965) y la época poscolonial (1965-presente) para ver hasta qué punto siguen vigentes los legados coloniales dentro de un contexto contemporáneo. Avanzamos la hipótesis que, de la larga residencia histórica y geográfica de las personas hispanomexicanas en el sudoeste, se han producidos textos simbólicos donde se registran dos o más discursos residuos cuyo origen es una ideología dominante. El capítulo 1 plantea y detalla la hipótesis, reseña los numerosos estudios existentes, describe el marco teórico y da la división en capítulos. En el capítulo 2, se da de manera detallada el método crítico: la definición del colonialismo clásico según la teoría de Mario Barrera, la relación colonizador/colonizado aportada por Albert Memmi y los conceptos del tercer espacio híbrido, el mestizaje y el imaginario decolonial asociados con la época poscolonial como ofrecidos respectivamente por Homi Bhabha, Rafael Pérez-Torres y Emma Pérez. El capítulo 3 ofrece un análisis de la época colonial española vía dos obras nuevomexicanas: el poema épico Historia de la Nueva México (1610) de Gaspar Pérez de Villagrá y el drama Los comanches (c.1779) de anónimo. El capítulo 4 trata la colonización angloamericana en las obras The Squatter and the Don (1885) de María Amparo Ruiz de Burton y Dew on the Thorn (escrita en los 1940; publicada en 1997) de Jovita González de Mireles. El capítulo 5 examina la época poscolonial vía la obra Los muertos también cuentan (1995) de Miguel Méndez. Una lectura de la literatura chicana/méxicosudoesteña revela la presencia de varios personajes típicos asociados cada uno a una diferente época histórica desde el conquistador español hasta un mexicano recién inmigrado, quienes no han podido evadir la correspondiente presencia de un grupo dominante u colonizador. Con base en una investigación de las cinco obras seleccionadas, se muestra cómo las relaciones coloniales se forman y se transforman y luego se manifiestan en un contexto contemporáneo, desplazando por ende nuestro entendimiento de las relaciones coloniales como un simple proyecto binario de dominación y subordinación.
ContributorsFonseca, Vanessa (Author) / Hernández-G., Manuel De Jesús (Thesis advisor) / Rosales, Jesus (Committee member) / García-Fernández, Carlos Javier (Committee member) / Volek, Emil (Committee member) / Horan, Elizabeth (Committee member) / Arizona State University (Publisher)
Created2013
Description
ABSTRACT Of all the writers associated with the McOndo movement, a literary movement that focuses on the reality of urban life for millions of young Latin Americans, Jorge Franco is perhaps the most distinguished. As the author of Paraíso Travel and Rosario Tijeras, Franco has expertly shown his international audience the brutal conditions under which so many residents of his birth city of Medellín, Colombia, live. In both novels the reader is introduced to a world in which various factors have set up a society characterized by victims and predators. This study will attempt to show how economics, violence, machismo, racism and class discrimination all play a role in establishing a social hierarchy that facilitates anti-social behavior, and how these social institutions perpetuate themselves to the detriment of those caught in the cycle.
ContributorsWise, Kenneth James (Author) / Volek, Emil (Thesis advisor) / Acereda, Alberto (Committee member) / García-Fernández, Carlos Javier (Committee member) / Arizona State University (Publisher)
Created2012
Description
Feature embeddings differ from raw features in the sense that the former obey certain properties like notion of similarity/dissimilarity in it's embedding space. word2vec is a preeminent example in this direction, where the similarity in the embedding space is measured in terms of the cosine similarity. Such language embedding models have seen numerous applications in both language and vision community as they capture the information in the modality (English language) efficiently. Inspired by these language models, this work focuses on learning embedding spaces for two visual computing tasks, 1. Image Hashing 2. Zero Shot Learning. The training set was used to learn embedding spaces over which similarity/dissimilarity is measured using several distance metrics like hamming / euclidean / cosine distances. While the above-mentioned language models learn generic word embeddings, in this work task specific embeddings were learnt which can be used for Image Retrieval and Classification separately.
Image Hashing is the task of mapping images to binary codes such that some notion of user-defined similarity is preserved. The first part of this work focuses on designing a new framework that uses the hash-tags associated with web images to learn the binary codes. Such codes can be used in several applications like Image Retrieval and Image Classification. Further, this framework requires no labelled data, leaving it very inexpensive. Results show that the proposed approach surpasses the state-of-art approaches by a significant margin.
Zero-shot classification is the task of classifying the test sample into a new class which was not seen during training. This is possible by establishing a relationship between the training and the testing classes using auxiliary information. In the second part of this thesis, a framework is designed that trains using the handcrafted attribute vectors and word vectors but doesn’t require the expensive attribute vectors during test time. More specifically, an intermediate space is learnt between the word vector space and the image feature space using the hand-crafted attribute vectors. Preliminary results on two zero-shot classification datasets show that this is a promising direction to explore.
Image Hashing is the task of mapping images to binary codes such that some notion of user-defined similarity is preserved. The first part of this work focuses on designing a new framework that uses the hash-tags associated with web images to learn the binary codes. Such codes can be used in several applications like Image Retrieval and Image Classification. Further, this framework requires no labelled data, leaving it very inexpensive. Results show that the proposed approach surpasses the state-of-art approaches by a significant margin.
Zero-shot classification is the task of classifying the test sample into a new class which was not seen during training. This is possible by establishing a relationship between the training and the testing classes using auxiliary information. In the second part of this thesis, a framework is designed that trains using the handcrafted attribute vectors and word vectors but doesn’t require the expensive attribute vectors during test time. More specifically, an intermediate space is learnt between the word vector space and the image feature space using the hand-crafted attribute vectors. Preliminary results on two zero-shot classification datasets show that this is a promising direction to explore.
ContributorsGattupalli, Jaya Vijetha (Author) / Li, Baoxin (Thesis advisor) / Yang, Yezhou (Committee member) / Venkateswara, Hemanth (Committee member) / Arizona State University (Publisher)
Created2019
Description
With the substantial development of intelligent robots, human-robot interaction (HRI) has become ubiquitous in applications such as collaborative manufacturing, surgical robotic operations, and autonomous driving. In all these applications, a human behavior model, which can provide predictions of human actions, is a helpful reference that helps robots to achieve intelligent interaction with humans. The requirement elicits an essential problem of how to properly model human behavior, especially when individuals are interacting or cooperating with each other. The major objective of this thesis is to utilize the human intention decoding method to help robots enhance their performance while interacting with humans. Preliminary work on integrating human intention estimation with an HRI scenario is shown to demonstrate the benefit. In order to achieve this goal, the research topic is divided into three phases. First, a novel method of an online measure of the human's reliance on the robot, which can be estimated through the intention decoding process from human actions，is described. An experiment that requires human participants to complete an object-moving task with a robot manipulator was conducted under different conditions of distractions. A relationship is discovered between human intention and trust while participants performed a familiar task with no distraction. This finding suggests a relationship between the psychological construct of trust and joint physical coordination, which bridges the human's action to its mental states. Then, a novel human collaborative dynamic model is introduced based on game theory and bounded rationality, which is a novel method to describe human dyadic behavior with the aforementioned theories. The mutual intention decoding process was also considered to inform this model. Through this model, the connection between the mental states of the individuals to their cooperative actions is indicated. A haptic interface is developed with a virtual environment and the experiments are conducted with 30 human subjects. The result suggests the existence of mutual intention decoding during the human dyadic cooperative behaviors. Last, the empirical results show that allowing agents to have empathy in inference, which lets the agents understand that others might have a false understanding of their intentions, can help to achieve correct intention inference. It has been verified that knowledge about vehicle dynamics was also important to correctly infer intentions. A new courteous policy is proposed that bounded the courteous motion using its inferred set of equilibrium motions. A simulation, which is set to reproduce an intersection passing case between an autonomous car and a human driving car, is conducted to demonstrate the benefit of the novel courteous control policy.
ContributorsWang, Yiwei (Author) / Zhang, Wenlong (Thesis advisor) / Berman, Spring (Committee member) / Lee, Hyunglae (Committee member) / Ren, Yi (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021
Description
Traditional Reinforcement Learning (RL) assumes to learn policies with respect to reward available from the environment but sometimes learning in a complex domain requires wisdom which comes from a wide range of experience. In behavior based robotics, it is observed that a complex behavior can be described by a combination of simpler behaviors. It is tempting to apply similar idea such that simpler behaviors can be combined in a meaningful way to tailor the complex combination. Such an approach would enable faster learning and modular design of behaviors. Complex behaviors can be combined with other behaviors to create even more advanced behaviors resulting in a rich set of possibilities. Similar to RL, combined behavior can keep evolving by interacting with the environment. The requirement of this method is to specify a reasonable set of simple behaviors. In this research, I present an algorithm that aims at combining behavior such that the resulting behavior has characteristics of each individual behavior. This approach has been inspired by behavior based robotics, such as the subsumption architecture and motor schema-based design. The combination algorithm outputs n weights to combine behaviors linearly. The weights are state dependent and change dynamically at every step in an episode. This idea is tested on discrete and continuous environments like OpenAI’s “Lunar Lander” and “Biped Walker”. Results are compared with related domains like Multi-objective RL, Hierarchical RL, Transfer learning, and basic RL. It is observed that the combination of behaviors is a novel way of learning which helps the agent achieve required characteristics. A combination is learned for a given state and so the agent is able to learn faster in an efficient manner compared to other similar approaches. Agent beautifully demonstrates characteristics of multiple behaviors which helps the agent to learn and adapt to the environment. Future directions are also suggested as possible extensions to this research.
ContributorsVora, Kevin Jatin (Author) / Zhang, Yu (Thesis advisor) / Yang, Yezhou (Committee member) / Praharaj, Sarbeswar (Committee member) / Arizona State University (Publisher)
Created2021
Description
Machine learning models can pick up biases and spurious correlations from training data and projects and amplify these biases during inference, thus posing significant challenges in real-world settings. One approach to mitigating this is a class of methods that can identify filter out bias-inducing samples from the training datasets to force models to avoid being exposed to biases. However, the filtering leads to a considerable wastage of resources as most of the dataset created is discarded as biased. This work deals with avoiding the wastage of resources by identifying and quantifying the biases. I further elaborate on the implications of dataset filtering on robustness (to adversarial attacks) and generalization (to out-of-distribution samples). The findings suggest that while dataset filtering does help to improve OOD(Out-Of-Distribution) generalization, it has a significant negative impact on robustness to adversarial attacks. It also shows that transforming bias-inducing samples into adversarial samples (instead of eliminating them from the dataset) can significantly boost robustness without sacrificing generalization.
ContributorsSachdeva, Bhavdeep Singh (Author) / Baral, Chitta (Thesis advisor) / Liu, Huan (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021
Description
There has been an explosion in the amount of data on the internet because of modern technology – especially image data – as a consequence of an exponential growth in the number of cameras existing in the world right now; from more extensive surveillance camera systems to billions of people walking around with smartphones in their pockets that come with built-in cameras. With this sudden increase in the accessibility of cameras, most of the data that is getting captured through these devices is ending up on the internet. Researchers soon took leverage of this data by creating large-scale datasets. However, generating a dataset – let alone a large-scale one – requires a lot of man-hours. This work presents an algorithm that makes use of optical flow and feature matching, along with utilizing localization outputs from a Mask R-CNN, to generate large-scale vehicle datasets without much human supervision. Additionally, this work proposes a novel multi-view vehicle dataset (MVVdb) of 500 vehicles which is also generated using the aforementioned algorithm.There are various research problems in computer vision that can leverage a multi-view dataset, e.g., 3D pose estimation, and 3D object detection. On the other hand, a multi-view vehicle dataset can be used for a 2D image to 3D shape prediction, generation of 3D vehicle models, and even a more robust vehicle make and model recognition. In this work, a ResNet is trained on the multi-view vehicle dataset to perform vehicle re-identification, which is fundamentally similar to a vehicle make and recognition problem – also showcasing the usability of the MVVdb dataset.
ContributorsGuha, Anubhab (Author) / Yang, Yezhou (Thesis advisor) / Lu, Duo (Committee member) / Banerjee, Ayan (Committee member) / Arizona State University (Publisher)
Created2022
Description
In recent years, there has been significant progress in deep learning and computer vision, with many models proposed that have achieved state-of-art results on various image recognition tasks. However, to explore the full potential of the advances in this field, there is an urgent need to push the processing of deep networks from the cloud to edge devices. Unfortunately, many deep learning models cannot be efficiently implemented on edge devices as these devices are severely resource-constrained. In this thesis, I present QU-Net, a lightweight binary segmentation model based on the U-Net architecture. Traditionally, neural networks consider the entire image to be significant. However, in real-world scenarios, many regions in an image do not contain any objects of significance. These regions can be removed from the original input allowing a network to focus on the relevant regions and thus reduce computational costs. QU-Net proposes the salient regions (binary mask) that the deeper models can use as the input. Experiments show that QU-Net helped achieve a computational reduction of 25% on the Microsoft Common Objects in Context (MS COCO) dataset and 57% on the Cityscapes dataset. Moreover, QU-Net is a generalizable model that outperforms other similar works, such as Dynamic Convolutions.
ContributorsSanthosh Kumar Varma, Rahul (Author) / Yang, Yezhou (Thesis advisor) / Fan, Deliang (Committee member) / Yang, Yingzhen (Committee member) / Arizona State University (Publisher)
Created2021