Matching Items (1,087)
Filtering by
- All Subjects: Computer Science
Description
Humans have an excellent ability to analyze and process information from multiple domains. They also possess the ability to apply the same decision-making process when the situation is familiar with their previous experience.
Inspired by human's ability to remember past experiences and apply the same when a similar situation occurs, the research community has attempted to augment memory with Neural Network to store the previously learned information. Together with this, the community has also developed mechanisms to perform domain-specific weight switching to handle multiple domains using a single model. Notably, the two research fields work independently, and the goal of this dissertation is to combine their capabilities.
This dissertation introduces a Neural Network module augmented with two external memories, one allowing the network to read and write the information and another to perform domain-specific weight switching. Two learning tasks are proposed in this work to investigate the model performance - solving mathematics operations sequence and action based on color sequence identification. A wide range of experiments with these two tasks verify the model's learning capabilities.
Inspired by human's ability to remember past experiences and apply the same when a similar situation occurs, the research community has attempted to augment memory with Neural Network to store the previously learned information. Together with this, the community has also developed mechanisms to perform domain-specific weight switching to handle multiple domains using a single model. Notably, the two research fields work independently, and the goal of this dissertation is to combine their capabilities.
This dissertation introduces a Neural Network module augmented with two external memories, one allowing the network to read and write the information and another to perform domain-specific weight switching. Two learning tasks are proposed in this work to investigate the model performance - solving mathematics operations sequence and action based on color sequence identification. A wide range of experiments with these two tasks verify the model's learning capabilities.
ContributorsPatel, Deep Chittranjan (Author) / Ben Amor, Hani (Thesis advisor) / Banerjee, Ayan (Committee member) / McDaniel, Troy (Committee member) / Arizona State University (Publisher)
Created2020
Description
Internet memes have become a widespread tool used by people for interacting and exchanging ideas over social media, blogs, and open messengers. Internet memes most commonly take the form of an image which is a combination of image, text, and humor, making them a powerful tool to deliver information. Image memes are used in viral marketing and mass advertising to propagate any ideas ranging from simple commercials to those that can cause changes and development in the social structures like countering hate speech.
This work proposes to treat automatic image meme generation as a translation process, and further present an end to end neural and probabilistic approach to generate an image-based meme for any given sentence using an encoder-decoder architecture. For a given input sentence, a meme is generated by combining a meme template image and a text caption where the meme template image is selected from a set of popular candidates using a selection module and the meme caption is generated by an encoder-decoder model. An encoder is used to map the selected meme template and the input sentence into a meme embedding space and then a decoder is used to decode the meme caption from the meme embedding space. The generated natural language caption is conditioned on the input sentence and the selected meme template.
The model learns the dependencies between the meme captions and the meme template images and generates new memes using the learned dependencies. The quality of the generated captions and the generated memes is evaluated through both automated metrics and human evaluation. An experiment is designed to score how well the generated memes can represent popular tweets from Twitter conversations. Experiments on Twitter data show the efficacy of the model in generating memes capable of representing a sentence in online social interaction.
This work proposes to treat automatic image meme generation as a translation process, and further present an end to end neural and probabilistic approach to generate an image-based meme for any given sentence using an encoder-decoder architecture. For a given input sentence, a meme is generated by combining a meme template image and a text caption where the meme template image is selected from a set of popular candidates using a selection module and the meme caption is generated by an encoder-decoder model. An encoder is used to map the selected meme template and the input sentence into a meme embedding space and then a decoder is used to decode the meme caption from the meme embedding space. The generated natural language caption is conditioned on the input sentence and the selected meme template.
The model learns the dependencies between the meme captions and the meme template images and generates new memes using the learned dependencies. The quality of the generated captions and the generated memes is evaluated through both automated metrics and human evaluation. An experiment is designed to score how well the generated memes can represent popular tweets from Twitter conversations. Experiments on Twitter data show the efficacy of the model in generating memes capable of representing a sentence in online social interaction.
ContributorsSadasivam, Aadhavan (Author) / Yang, Yezhou (Thesis advisor) / Baral, Chitta (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2020
Description
The problem of multiple object tracking seeks to jointly estimate the time-varying cardinality and trajectory of each object. There are numerous challenges that are encountered in tracking multiple objects including a time-varying number of measurements, under varying constraints, and environmental conditions. In this thesis, the proposed statistical methods integrate the use of physical-based models with Bayesian nonparametric methods to address the main challenges in a tracking problem. In particular, Bayesian nonparametric methods are exploited to efficiently and robustly infer object identity and learn time-dependent cardinality; together with Bayesian inference methods, they are also used to associate measurements to objects and estimate the trajectory of objects. These methods differ from the current methods to the core as the existing methods are mainly based on random finite set theory.
The first contribution proposes dependent nonparametric models such as the dependent Dirichlet process and the dependent Pitman-Yor process to capture the inherent time-dependency in the problem at hand. These processes are used as priors for object state distributions to learn dependent information between previous and current time steps. Markov chain Monte Carlo sampling methods exploit the learned information to sample from posterior distributions and update the estimated object parameters.
The second contribution proposes a novel, robust, and fast nonparametric approach based on a diffusion process over infinite random trees to infer information on object cardinality and trajectory. This method follows the hierarchy induced by objects entering and leaving a scene and the time-dependency between unknown object parameters. Markov chain Monte Carlo sampling methods integrate the prior distributions over the infinite random trees with time-dependent diffusion processes to update object states.
The third contribution develops the use of hierarchical models to form a prior for statistically dependent measurements in a single object tracking setup. Dependency among the sensor measurements provides extra information which is incorporated to achieve the optimal tracking performance. The hierarchical Dirichlet process as a prior provides the required flexibility to do inference. Bayesian tracker is integrated with the hierarchical Dirichlet process prior to accurately estimate the object trajectory.
The fourth contribution proposes an approach to model both the multiple dependent objects and multiple dependent measurements. This approach integrates the dependent Dirichlet process modeling over the dependent object with the hierarchical Dirichlet process modeling of the measurements to fully capture the dependency among both object and measurements. Bayesian nonparametric models can successfully associate each measurement to the corresponding object and exploit dependency among them to more accurately infer the trajectory of objects. Markov chain Monte Carlo methods amalgamate the dependent Dirichlet process with the hierarchical Dirichlet process to infer the object identity and object cardinality.
Simulations are exploited to demonstrate the improvement in multiple object tracking performance when compared to approaches that are developed based on random finite set theory.
The first contribution proposes dependent nonparametric models such as the dependent Dirichlet process and the dependent Pitman-Yor process to capture the inherent time-dependency in the problem at hand. These processes are used as priors for object state distributions to learn dependent information between previous and current time steps. Markov chain Monte Carlo sampling methods exploit the learned information to sample from posterior distributions and update the estimated object parameters.
The second contribution proposes a novel, robust, and fast nonparametric approach based on a diffusion process over infinite random trees to infer information on object cardinality and trajectory. This method follows the hierarchy induced by objects entering and leaving a scene and the time-dependency between unknown object parameters. Markov chain Monte Carlo sampling methods integrate the prior distributions over the infinite random trees with time-dependent diffusion processes to update object states.
The third contribution develops the use of hierarchical models to form a prior for statistically dependent measurements in a single object tracking setup. Dependency among the sensor measurements provides extra information which is incorporated to achieve the optimal tracking performance. The hierarchical Dirichlet process as a prior provides the required flexibility to do inference. Bayesian tracker is integrated with the hierarchical Dirichlet process prior to accurately estimate the object trajectory.
The fourth contribution proposes an approach to model both the multiple dependent objects and multiple dependent measurements. This approach integrates the dependent Dirichlet process modeling over the dependent object with the hierarchical Dirichlet process modeling of the measurements to fully capture the dependency among both object and measurements. Bayesian nonparametric models can successfully associate each measurement to the corresponding object and exploit dependency among them to more accurately infer the trajectory of objects. Markov chain Monte Carlo methods amalgamate the dependent Dirichlet process with the hierarchical Dirichlet process to infer the object identity and object cardinality.
Simulations are exploited to demonstrate the improvement in multiple object tracking performance when compared to approaches that are developed based on random finite set theory.
ContributorsMoraffah, Bahman (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Bliss, Daniel W. (Committee member) / Richmond, Christ D. (Committee member) / Dasarathy, Gautam (Committee member) / Arizona State University (Publisher)
Created2019
Description
Autonomous vehicle technology has been evolving for years since the Automated Highway System Project. However, this technology has been under increased scrutiny ever since an autonomous vehicle killed Elaine Herzberg, who was crossing the street in Tempe, Arizona in March 2018. Recent tests of autonomous vehicles on public roads have faced opposition from nearby residents. Before these vehicles are widely deployed, it is imperative that the general public trusts them. For this, the vehicles must be able to identify objects in their surroundings and demonstrate the ability to follow traffic rules while making decisions with human-like moral integrity when confronted with an ethical dilemma, such as an unavoidable crash that will injure either a pedestrian or the passenger.
Testing autonomous vehicles in real-world scenarios would pose a threat to people and property alike. A safe alternative is to simulate these scenarios and test to ensure that the resulting programs can work in real-world scenarios. Moreover, in order to detect a moral dilemma situation quickly, the vehicle should be able to identify objects in real-time while driving. Toward this end, this thesis investigates the use of cross-platform training for neural networks that perform visual identification of common objects in driving scenarios. Here, the object detection algorithm Faster R-CNN is used. The hypothesis is that it is possible to train a neural network model to detect objects from two different domains, simulated or physical, using transfer learning. As a proof of concept, an object detection model is trained on image datasets extracted from CARLA, a virtual driving environment, via transfer learning. After bringing the total loss factor to 0.4, the model is evaluated with an IoU metric. It is determined that the model has a precision of 100% and 75% for vehicles and traffic lights respectively. The recall is found to be 84.62% and 75% for the same. It is also shown that this model can detect the same classes of objects from other virtual environments and real-world images. Further modifications to the algorithm that may be required to improve performance are discussed as future work.
Testing autonomous vehicles in real-world scenarios would pose a threat to people and property alike. A safe alternative is to simulate these scenarios and test to ensure that the resulting programs can work in real-world scenarios. Moreover, in order to detect a moral dilemma situation quickly, the vehicle should be able to identify objects in real-time while driving. Toward this end, this thesis investigates the use of cross-platform training for neural networks that perform visual identification of common objects in driving scenarios. Here, the object detection algorithm Faster R-CNN is used. The hypothesis is that it is possible to train a neural network model to detect objects from two different domains, simulated or physical, using transfer learning. As a proof of concept, an object detection model is trained on image datasets extracted from CARLA, a virtual driving environment, via transfer learning. After bringing the total loss factor to 0.4, the model is evaluated with an IoU metric. It is determined that the model has a precision of 100% and 75% for vehicles and traffic lights respectively. The recall is found to be 84.62% and 75% for the same. It is also shown that this model can detect the same classes of objects from other virtual environments and real-world images. Further modifications to the algorithm that may be required to improve performance are discussed as future work.
ContributorsSankaramangalam Ulhas, Sangeet (Author) / Berman, Spring (Thesis advisor) / Johnson, Kathryn (Committee member) / Yong, Sze Zheng (Committee member) / Arizona State University (Publisher)
Created2019
Description
Many researchers have seen the value blockchain can add to the field of voting and many protocols have been proposed to allow voting to be conducted in a way that takes advantage of blockchains distributed and immutable structure. While blockchains immutable structure can take the place of paper records in preventing tampering it by itself is insufficient to construct a trustworthy voting system with eligibility, privacy, verifiability, and fairness requirements. Many of the protocols which strive to keep voters votes confidential, but also allow for verifiability and eligibility requirements rely on either a blind signature provided by a central authority to provide compliance with these requirements or ring signatures to prove membership in the set of voters. A blind signature issued by a central authority introduces a potential vulnerability as it allows a corrupt central authority to pass a large number of forged ballots into the mix without any detection. Ring signatures on the other hand tend to be overly resource intensive to allow for practical usage in large voting sets. The research in this thesis focuses on improving the trustworthiness of electronic voting systems by providing possible ways of avoiding or detecting corrupt central authorities while still relying upon the benefits of efficiency the blind signature provides.
ContributorsAnderson, Brandon David (Author) / Yau, Stephen S. (Thesis advisor) / Dasgupta, Partha (Committee member) / Marchant, Gary (Committee member) / Arizona State University (Publisher)
Created2020
Description
The pervasive use of the Web has connected billions of people all around the globe and enabled them to obtain information at their fingertips. This results in tremendous amounts of user-generated data which makes users traceable and vulnerable to privacy leakage attacks. In general, there are two types of privacy leakage attacks for user-generated data, i.e., identity disclosure and private-attribute disclosure attacks. These attacks put users at potential risks ranging from persecution by governments to targeted frauds. Therefore, it is necessary for users to be able to safeguard their privacy without leaving their unnecessary traces of online activities. However, privacy protection comes at the cost of utility loss defined as the loss in quality of personalized services users receive. The reason is that this information of traces is crucial for online vendors to provide personalized services and a lack of it would result in deteriorating utility. This leads to a dilemma of privacy and utility.
Protecting users' privacy while preserving utility for user-generated data is a challenging task. The reason is that users generate different types of data such as Web browsing histories, user-item interactions, and textual information. This data is heterogeneous, unstructured, noisy, and inherently different from relational and tabular data and thus requires quantifying users' privacy and utility in each context separately. In this dissertation, I investigate four aspects of protecting user privacy for user-generated data. First, a novel adversarial technique is introduced to assay privacy risks in heterogeneous user-generated data. Second, a novel framework is proposed to boost users' privacy while retaining high utility for Web browsing histories. Third, a privacy-aware recommendation system is developed to protect privacy w.r.t. the rich user-item interaction data by recommending relevant and privacy-preserving items. Fourth, a privacy-preserving framework for text representation learning is presented to safeguard user-generated textual data as it can reveal private information.
Protecting users' privacy while preserving utility for user-generated data is a challenging task. The reason is that users generate different types of data such as Web browsing histories, user-item interactions, and textual information. This data is heterogeneous, unstructured, noisy, and inherently different from relational and tabular data and thus requires quantifying users' privacy and utility in each context separately. In this dissertation, I investigate four aspects of protecting user privacy for user-generated data. First, a novel adversarial technique is introduced to assay privacy risks in heterogeneous user-generated data. Second, a novel framework is proposed to boost users' privacy while retaining high utility for Web browsing histories. Third, a privacy-aware recommendation system is developed to protect privacy w.r.t. the rich user-item interaction data by recommending relevant and privacy-preserving items. Fourth, a privacy-preserving framework for text representation learning is presented to safeguard user-generated textual data as it can reveal private information.
ContributorsBeigi, Ghazaleh (Author) / Liu, Huan (Thesis advisor) / Kambhampati, Subbarao (Committee member) / Tong, Hanghang (Committee member) / Eliassi-Rad, Tina (Committee member) / Arizona State University (Publisher)
Created2020
Description
The recent proliferation of online platforms has not only revolutionized the way people communicate and acquire information but has also led to propagation of malicious information (e.g., online human trafficking, spread of misinformation, etc.). Propagation of such information occurs at unprecedented scale that could ultimately pose imminent societal-significant threats to the public. To better understand the behavior and impact of the malicious actors and counter their activity, social media authorities need to deploy certain capabilities to reduce their threats. Due to the large volume of this data and limited manpower, the burden usually falls to automatic approaches to identify these malicious activities. However, this is a subtle task facing online platforms due to several challenges: (1) malicious users have strong incentives to disguise themselves as normal users (e.g., intentional misspellings, camouflaging, etc.), (2) malicious users are high likely to be key users in making harmful messages go viral and thus need to be detected at their early life span to stop their threats from reaching a vast audience, and (3) available data for training automatic approaches for detecting malicious users, are usually either highly imbalanced (i.e., higher number of normal users than malicious users) or comprise insufficient labeled data.
To address the above mentioned challenges, in this dissertation I investigate the propagation of online malicious information from two broad perspectives: (1) content posted by users and (2) information cascades formed by resharing mechanisms in social media. More specifically, first, non-parametric and semi-supervised learning algorithms are introduced to discern potential patterns of human trafficking activities that are of high interest to law enforcement. Second, a time-decay causality-based framework is introduced for early detection of “Pathogenic Social Media (PSM)” accounts (e.g., terrorist supporters). Third, due to the lack of sufficient annotated data for training PSM detection approaches, a semi-supervised causal framework is proposed that utilizes causal-related attributes from unlabeled instances to compensate for the lack of enough labeled data. Fourth, a feature-driven approach for PSM detection is introduced that leverages different sets of attributes from users’ causal activities, account-level and content-related information as well as those from URLs shared by users.
To address the above mentioned challenges, in this dissertation I investigate the propagation of online malicious information from two broad perspectives: (1) content posted by users and (2) information cascades formed by resharing mechanisms in social media. More specifically, first, non-parametric and semi-supervised learning algorithms are introduced to discern potential patterns of human trafficking activities that are of high interest to law enforcement. Second, a time-decay causality-based framework is introduced for early detection of “Pathogenic Social Media (PSM)” accounts (e.g., terrorist supporters). Third, due to the lack of sufficient annotated data for training PSM detection approaches, a semi-supervised causal framework is proposed that utilizes causal-related attributes from unlabeled instances to compensate for the lack of enough labeled data. Fourth, a feature-driven approach for PSM detection is introduced that leverages different sets of attributes from users’ causal activities, account-level and content-related information as well as those from URLs shared by users.
ContributorsAlvari, Hamidreza (Author) / Shakarian, Paulo (Thesis advisor) / Davulcu, Hasan (Committee member) / Tong, Hanghang (Committee member) / Ruston, Scott (Committee member) / Arizona State University (Publisher)
Created2020
Description
The ubiquity of single camera systems in society has made improving monocular depth estimation a topic of increasing interest in the broader computer vision community. Inspired by recent work in sparse-to-dense depth estimation, this thesis focuses on sparse patterns generated from feature detection based algorithms as opposed to regular grid sparse patterns used by previous work. This work focuses on using these feature-based sparse patterns to generate additional depth information by interpolating regions between clusters of samples that are in close proximity to each other. These interpolated sparse depths are used to enforce additional constraints on the network’s predictions. In addition to the improved depth prediction performance observed from incorporating the sparse sample information in the network compared to pure RGB-based methods, the experiments show that actively retraining a network on a small number of samples that deviate most from the interpolated sparse depths leads to better depth prediction overall.
This thesis also introduces a new metric, titled Edge, to quantify model performance in regions of an image that show the highest change in ground truth depth values along either the x-axis or the y-axis. Existing metrics in depth estimation like Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) quantify model performance across the entire image and don’t focus on specific regions of an image that are hard to predict. To this end, the proposed Edge metric focuses specifically on these hard to classify regions. The experiments also show that using the Edge metric as a small addition to existing loss functions like L1 loss in current state-of-the-art methods leads to vastly improved performance in these hard to classify regions, while also improving performance across the board in every other metric.
This thesis also introduces a new metric, titled Edge, to quantify model performance in regions of an image that show the highest change in ground truth depth values along either the x-axis or the y-axis. Existing metrics in depth estimation like Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) quantify model performance across the entire image and don’t focus on specific regions of an image that are hard to predict. To this end, the proposed Edge metric focuses specifically on these hard to classify regions. The experiments also show that using the Edge metric as a small addition to existing loss functions like L1 loss in current state-of-the-art methods leads to vastly improved performance in these hard to classify regions, while also improving performance across the board in every other metric.
ContributorsRai, Anshul (Author) / Yang, Yezhou (Thesis advisor) / Zhang, Wenlong (Committee member) / Liang, Jianming (Committee member) / Arizona State University (Publisher)
Created2019
Description
In combinatorial mathematics, a Steiner system is a type of block design. A Steiner triple system is a special case of Steiner system where all blocks contain 3 elements and each pair of points occurs in exactly one block. Independent sets in Steiner triple systems is the topic which is discussed in this thesis. Some properties related to independent sets in Steiner triple system are provided. The distribution of sizes of maximum independent sets of Steiner triple systems of specific order is also discussed in this thesis. An algorithm for constructing a Steiner triple system with maximum independent set whose size is restricted with a lower bound is provided. An alternative way to construct a Steiner triple system using an affine plane is also presented. A modified greedy algorithm for finding a maximal independent set in a Steiner triple system and a post-optimization method for improving the results yielded by this algorithm are established.
ContributorsWang, Zhaomeng (Author) / Colbourn, Charles (Thesis advisor) / Richa, Andrea (Committee member) / Jiang, Zilin (Committee member) / Arizona State University (Publisher)
Created2021
Description
In videos that contain actions performed unintentionally, agents do not achieve their desired goals. In such videos, it is challenging for computer vision systems to understand high-level concepts such as goal-directed behavior. On the other hand, from a very early age, humans are able to understand the relation between an agent and their ultimate goal even if the action gets disrupted or unintentional effects occur. Inculcating this ability in artificially intelligent agents would make them better social learners by not just learning from their own mistakes, i.e, reinforcement learning, but also learning from other's mistakes. For example, this could greatly reduce the search space for artificially intelligent agents for finding the correct action sequence when trying to achieve a new goal, since they would be able to learn from others what not to do as well as how/when actions result in undesired outcomes.To validate this ability of deep learning models to perform this task, the Weakly Augmented Oops (W-Oops) dataset is proposed, built upon the Oops dataset. W-Oops consists of 2,100 unintentional human action videos, with 44 goal-directed and 33 unintentional video-level activity labels collected through human annotations.
Inspired by previous methods on tasks such as weakly supervised action localization which show promise for achieving good localization results without ground truth segment annotations, this paper proposes a weakly supervised algorithm for localizing the goal-directed as well as the unintentional temporal region of a video using only video-level labels. In particular, an attention mechanism based strategy is employed that predicts the temporal regions which contributes the most to a classification task, leveraging solely video-level labels. Meanwhile, our designed overlap regularization allows the model to focus on distinct portions of the video for inferring the goal-directed and unintentional activity, while guaranteeing their temporal ordering. Extensive quantitative experiments verify the validity of our localization method.
ContributorsChakravarthy, Arnav (Author) / Yang, Yezhou (Thesis advisor) / Davulcu, Hasan (Committee member) / Pavlic, Theodore (Committee member) / Arizona State University (Publisher)
Created2021