Matching Items (51)
Filtering by
- All Subjects: Machine Learning
- Creators: School of Mathematical and Statistical Sciences
- Creators: Yang, Yezhou
Description
The performance of most of the visual computing tasks depends on the quality of the features extracted from the raw data. Insightful feature representation increases the performance of many learning algorithms by exposing the underlying explanatory factors of the output for the unobserved input. A good representation should also handle anomalies in the data such as missing samples and noisy input caused by the undesired, external factors of variation. It should also reduce the data redundancy. Over the years, many feature extraction processes have been invented to produce good representations of raw images and videos.
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 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.
ContributorsChandakkar, Parag Shridhar (Author) / Li, Baoxin (Thesis advisor) / Yang, Yezhou (Committee member) / Turaga, Pavan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2017
Description
Handwritten documents have gained popularity in various domains including education and business. A key task in analyzing a complex document is to distinguish between various content types such as text, math, graphics, tables and so on. For example, one such aspect could be a region on the document with a mathematical expression; in this case, the label would be math. This differentiation facilitates the performance of specific recognition tasks depending on the content type. We hypothesize that the recognition accuracy of the subsequent tasks such as textual, math, and shape recognition will increase, further leading to a better analysis of the document.
Content detection on handwritten documents assigns a particular class to a homogeneous portion of the document. To complete this task, a set of handwritten solutions was digitally collected from middle school students located in two different geographical regions in 2017 and 2018. This research discusses the methods to collect, pre-process and detect content type in the collected handwritten documents. A total of 4049 documents were extracted in the form of image, and json format; and were labelled using an object labelling software with tags being text, math, diagram, cross out, table, graph, tick mark, arrow, and doodle. The labelled images were fed to the Tensorflow’s object detection API to learn a neural network model. We show our results from two neural networks models, Faster Region-based Convolutional Neural Network (Faster R-CNN) and Single Shot detection model (SSD).
Content detection on handwritten documents assigns a particular class to a homogeneous portion of the document. To complete this task, a set of handwritten solutions was digitally collected from middle school students located in two different geographical regions in 2017 and 2018. This research discusses the methods to collect, pre-process and detect content type in the collected handwritten documents. A total of 4049 documents were extracted in the form of image, and json format; and were labelled using an object labelling software with tags being text, math, diagram, cross out, table, graph, tick mark, arrow, and doodle. The labelled images were fed to the Tensorflow’s object detection API to learn a neural network model. We show our results from two neural networks models, Faster Region-based Convolutional Neural Network (Faster R-CNN) and Single Shot detection model (SSD).
ContributorsFaizaan, Shaik Mohammed (Author) / VanLehn, Kurt (Thesis advisor) / Cheema, Salman Shaukat (Thesis advisor) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2018
Description
Reinforcement learning (RL) is a powerful methodology for teaching autonomous agents complex behaviors and skills. A critical component in most RL algorithms is the reward function -- a mathematical function that provides numerical estimates for desirable and undesirable states. Typically, the reward function must be hand-designed by a human expert and, as a result, the scope of a robot's autonomy and ability to safely explore and learn in new and unforeseen environments is constrained by the specifics of the designed reward function. In this thesis, I design and implement a stateful collision anticipation model with powerful predictive capability based upon my research of sequential data modeling and modern recurrent neural networks. I also develop deep reinforcement learning methods whose rewards are generated by self-supervised training and intrinsic signals. The main objective is to work towards the development of resilient robots that can learn to anticipate and avoid damaging interactions by combining visual and proprioceptive cues from internal sensors. The introduced solutions are inspired by pain pathways in humans and animals, because such pathways are known to guide decision-making processes and promote self-preservation. A new "robot dodge ball' benchmark is introduced in order to test the validity of the developed algorithms in dynamic environments.
ContributorsRichardson, Trevor W (Author) / Ben Amor, Heni (Thesis advisor) / Yang, Yezhou (Committee member) / Srivastava, Siddharth (Committee member) / Arizona State University (Publisher)
Created2018
Description
Bots tamper with social media networks by artificially inflating the popularity of certain topics. In this paper, we define what a bot is, we detail different motivations for bots, we describe previous work in bot detection and observation, and then we perform bot detection of our own. For our bot detection, we are interested in bots on Twitter that tweet Arabic extremist-like phrases. A testing dataset is collected using the honeypot method, and five different heuristics are measured for their effectiveness in detecting bots. The model underperformed, but we have laid the ground-work for a vastly untapped focus on bot detection: extremist ideal diffusion through bots.
ContributorsKarlsrud, Mark C. (Author) / Liu, Huan (Thesis director) / Morstatter, Fred (Committee member) / Barrett, The Honors College (Contributor) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2015-05
Description
The OMFIT (One Modeling Framework for Integrated Tasks) modeling environment and the BRAINFUSE module have been deployed on the PPPL (Princeton Plasma Physics Laboratory) computing cluster with modifications that have rendered the application of artificial neural networks (NNs) to the TRANSP databases for the JET (Joint European Torus), TFTR (Tokamak Fusion Test Reactor), and NSTX (National Spherical Torus Experiment) devices possible through their use. This development has facilitated the investigation of NNs for predicting heat transport profiles in JET, TFTR, and NSTX, and has promoted additional investigations to discover how else NNs may be of use to scientists at PPPL. In applying NNs to the aforementioned devices for predicting heat transport, the primary goal of this endeavor is to reproduce the success shown in Meneghini et al. in using NNs for heat transport prediction in DIII-D. Being able to reproduce the results from is important because this in turn would provide scientists at PPPL with a quick and efficient toolset for reliably predicting heat transport profiles much faster than any existing computational methods allow; the progress towards this goal is outlined in this report, and potential additional applications of the NN framework are presented.
ContributorsLuna, Christopher Joseph (Author) / Tang, Wenbo (Thesis director) / Treacy, Michael (Committee member) / Orso, Meneghini (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Department of Physics (Contributor)
Created2015-05
Description
Twitter, the microblogging platform, has grown in prominence to the point that the topics that trend on the network are often the subject of the news and other traditional media. By predicting trends on Twitter, it could be possible to predict the next major topic of interest to the public. With this motivation, this paper develops a model for trends leveraging previous work with k-nearest-neighbors and dynamic time warping. The development of this model provides insight into the length and features of trends, and successfully generalizes to identify 74.3% of trends in the time period of interest. The model developed in this work provides understanding into why par- ticular words trend on Twitter.
ContributorsMarshall, Grant A (Author) / Liu, Huan (Thesis director) / Morstatter, Fred (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2015-05
Description
A model has been developed to modify Euler-Bernoulli beam theory for wooden beams, using visible properties of wood knot-defects. Treating knots in a beam as a system of two ellipses that change the local bending stiffness has been shown to improve the fit of a theoretical beam displacement function to edge-line deflection data extracted from digital imagery of experimentally loaded beams. In addition, an Ellipse Logistic Model (ELM) has been proposed, using L1-regularized logistic regression, to predict the impact of a knot on the displacement of a beam. By classifying a knot as severely positive or negative, vs. mildly positive or negative, ELM can classify knots that lead to large changes to beam deflection, while not over-emphasizing knots that may not be a problem. Using ELM with a regression-fit Young's Modulus on three-point bending of Douglass Fir, it is possible estimate the effects a knot will have on the shape of the resulting displacement curve.
ContributorsSexton, Thurston Bryant (Author) / Takahashi, Timothy (Thesis director) / Jones, Donald (Committee member) / Barrett, The Honors College (Contributor) / Mechanical and Aerospace Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / School of Human Evolution and Social Change (Contributor)
Created2015-05
Description
In the field of machine learning, reinforcement learning stands out for its ability to explore approaches to complex, high dimensional problems that outperform even expert humans. For robotic locomotion tasks reinforcement learning provides an approach to solving them without the need for unique controllers. In this thesis, two reinforcement learning algorithms, Deep Deterministic Policy Gradient and Group Factor Policy Search are compared based upon their performance in the bipedal walking environment provided by OpenAI gym. These algorithms are evaluated on their performance in the environment and their sample efficiency.
ContributorsMcDonald, Dax (Author) / Ben Amor, Heni (Thesis director) / Yang, Yezhou (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2018-12
Description
Cryptocurrencies have become one of the most fascinating forms of currency and economics due to their fluctuating values and lack of centralization. This project attempts to use machine learning methods to effectively model in-sample data for Bitcoin and Ethereum using rule induction methods. The dataset is cleaned by removing entries with missing data. The new column is created to measure price difference to create a more accurate analysis on the change in price. Eight relevant variables are selected using cross validation: the total number of bitcoins, the total size of the blockchains, the hash rate, mining difficulty, revenue from mining, transaction fees, the cost of transactions and the estimated transaction volume. The in-sample data is modeled using a simple tree fit, first with one variable and then with eight. Using all eight variables, the in-sample model and data have a correlation of 0.6822657. The in-sample model is improved by first applying bootstrap aggregation (also known as bagging) to fit 400 decision trees to the in-sample data using one variable. Then the random forests technique is applied to the data using all eight variables. This results in a correlation between the model and data of 9.9443413. The random forests technique is then applied to an Ethereum dataset, resulting in a correlation of 9.6904798. Finally, an out-of-sample model is created for Bitcoin and Ethereum using random forests, with a benchmark correlation of 0.03 for financial data. The correlation between the training model and the testing data for Bitcoin was 0.06957639, while for Ethereum the correlation was -0.171125. In conclusion, it is confirmed that cryptocurrencies can have accurate in-sample models by applying the random forests method to a dataset. However, out-of-sample modeling is more difficult, but in some cases better than typical forms of financial data. It should also be noted that cryptocurrency data has similar properties to other related financial datasets, realizing future potential for system modeling for cryptocurrency within the financial world.
ContributorsBrowning, Jacob Christian (Author) / Meuth, Ryan (Thesis director) / Jones, Donald (Committee member) / McCulloch, Robert (Committee member) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Machine learning for analytics has exponentially increased in the past few years due to its ability to identify hidden insights in data. It also has a plethora of applications in healthcare ranging from improving image recognition in CT scans to extracting semantic meaning from thousands of medical form PDFs. Currently in the BioElectrical Systems and Technology Lab, there is a biosensor in development that retrieves and analyzes data manually. In a proof of concept, this project uses the neural network architecture to automatically parse and classify a cardiac disease data set as well as explore health related factors impacting cardiac disease in patients of all ages.
ContributorsMurella, Akhila Sainagaki (Author) / Blain-Christen, Jennifer (Thesis director) / Meuth, Ryan (Committee member) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / School of the Arts, Media and Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05