Computer Sciences Commons^™

Probabilistic Spiking Neural Networks : Supervised, Unsupervised And Adversarial Trainings, Alireza Bagheri

Dissertations

Spiking Neural Networks (SNNs), or third-generation neural networks, are networks of computation units, called neurons, in which each neuron with internal analogue dynamics receives as input and produces as output spiking, that is, binary sparse, signals. In contrast, second-generation neural networks, termed as Artificial Neural Networks (ANNs), rely on simple static non-linear neurons that are known to be energy-intensive, hindering their implementations on energy-limited processors such as mobile devices. The sparse event-based characteristics of SNNs for information transmission and encoding have made them more feasible for highly energy-efficient neuromorphic computing architectures. The most existing training algorithms for SNNs are based …

Statistical Machine Learning Methods For Mining Spatial And Temporal Data, Fei Tan

Dissertations

Spatial and temporal dependencies are ubiquitous properties of data in numerous domains. The popularity of spatial and temporal data mining has thus grown with the increasing prevalence of massive data. The presence of spatial and temporal attributes not only provides complementary useful perspectives, but also poses new challenges to the representation and integration into the learning procedure. In this dissertation, the involved spatial and temporal dependencies are explored with three genres: sample-wise, feature-wise, and target-wise. A family of novel methodologies is developed accordingly for the dependency representation in respective scenarios.

First, dependencies among discrete, continuous and repeated observations are studied …

Deep Morphological Neural Networks, Yucong Shen

Theses

Mathematical morphology is a theory and technique applied to collect features like geometric and topological structures in digital images. Determining suitable morphological operations and structuring elements for a give purpose is a cumbersome and time-consuming task. In this paper, morphological neural networks are proposed to address this problem. Serving as a non-linear feature extracting layers in deep learning frameworks, the efficiency of the proposed morphological layer is confirmed analytically and empirically. With a known target, a single-filter morphological layer learns the structuring element correctly, and an adaptive layer can automatically select appropriate morphological operations. For high level applications, the proposed …

Confucian Robot Ethics, Qin Zhu, Tom Williams, Ruchen Wen

Computer Ethics - Philosophical Enquiry (CEPE) Proceedings

In the literature of artificial moral agents (AMAs), most work is influenced by either deontological or utilitarian frameworks. It has also been widely acknowledged that these Western “rule-based” ethical theories have encountered both philosophical and computing challenges. To tackle these challenges, this paper explores a non-Western, role-based, Confucian approach to robot ethics. In this paper, we start by providing a short introduction to some theoretical fundamentals of Confucian ethics. Then, we discuss some very preliminary ideas for constructing a Confucian approach to robot ethics. Lastly, we briefly share a couple of empirical studies our research group has recently conducted that …

Human Supremacy As Posthuman Risk, Daniel Estrada

Computer Ethics - Philosophical Enquiry (CEPE) Proceedings

Human supremacy is the widely held view that human interests ought to be privileged over other interests as a matter of public policy. Posthumanism is an historical and cultural situation characterized by a critical reevaluation of anthropocentrist theory and practice. This paper draws on Rosi Braidotti’s critical posthumanism and the critique of ideal theory in Charles Mills and Serene Khader to address the use of human supremacist rhetoric in AI ethics and policy discussions, particularly in the work of Joanna Bryson. This analysis leads to identifying a set of risks posed by human supremacist policy in a posthuman context, specifically …

Autonomous Vehicles And The Ethical Tension Between Occupant And Non-Occupant Safety, Jason Borenstein, Joseph Herkert, Keith W. Miller

Computer Ethics - Philosophical Enquiry (CEPE) Proceedings

Autonomous vehicle manufacturers, people inside an autonomous vehicle (occupants), and people outside the vehicle (non-occupants) are among the distinct stakeholders when addressing ethical issues inherent in systems that include autonomous vehicles. As responses to recent tragic cases illustrate, advocates for autonomous vehicles tend to focus on occupant safety, sometimes to the exclusion of non-occupant safety. Thus, we aim to examine ethical issues associated with non-occupant safety, including pedestrians, bicyclists, motorcyclists, and riders of motorized scooters. We also explore the ethical implications of technical and policy ideas that some might propose to improve non-occupant safety. In addition, if safety (writ large) …

Keeping Anonymity At The Consumer Behavior On The Internet: Proof Of Sacrifice, Sachio Horie

Computer Ethics - Philosophical Enquiry (CEPE) Proceedings

The evolution of the Internet and AI technology has made it possible for the government and the businesses to keep track of their personal lives. GAFA continues to collect information unintended by the individuals. It is a threat that our privacy is violated in this way. In order to solute such problems, it is important to consider a mechanism that enables us to be peaceful lives while protecting privacy in the Internet society.

This paper focuses on the consumption behavior on the Internet and addresses anonymity. We consider some network protocols that enable sustainable consensus by combining anonymity methods such …

Designing Single Guide Rnas For Crispr/Cas9, Neha Atul Bhagwat

Master's Projects

Researchers have been working towards development of tools to facilitate regular use genome engineering techniques. In recent years, the focus of these efforts has been the Clustered Regularly Interspaced Short Palindromic Repeats(CRISPR)/CRISPR associated(Cas) systems. These systems, while found naturally in bacteria and archaea as an immunity mechanism, can be used for genome engineering in eukaryotes.

There are three major computational challenges associated with the use of CRISPR/Cas9 in genome engineering for mammals - identification of CRISPR arrays, single guide RNA design and minimizing off-target effects. This project attempts to solve the problem of single guide RNA design using a novel …

Context-Based Multi-Stage Offline Handwritten Mathematical Symbol Recognition Using Deep Learning, Sui Kun Guan

Master's Projects

We propose a multi-stage machine learning (ML) architecture to improve the accuracy of offline handwritten mathematical symbol recognition. In the first stage, we train and assemble multiple deep convolutional neural networks to classify isolated mathematical symbols. However, certain ambiguous symbols are hard to classify without the context information of the mathematical expressions where the symbols belong. In the second stage, we train a deep convolutional neural network that further classifies the ambiguous symbols based on the context information of the symbols. To further improve the classification accuracy, in the third stage, we develop a set of rules to classify the …

Machine Learning In Crop Classification Of Temporal Multispectral Satellite Image, Ravali Koppaka

Master's Projects

Recently, there has been a remarkable growth in Artificial Intelligence (AI) with

the development of efficient AI models and high-power computational resources for processing complex datasets. There has been a growing number of applications of machine learning in satellite remote sensing image data processing. In this work, machine learning methods were applied for crop classification of temporal multi- spectral satellite image to achieve better prediction of crop-wise area statistics. In India, agriculture has a huge impact on the national economy and most of the critical decisions are dependent on agricultural statistics. Sentinel-2 satellite image data for the Guntur district region …

Learning For Free – Object Detectors Trained On Synthetic Data, Charles Thane Mackay

Master's Projects

A picture is worth a thousand words, or if you want it labeled, it’s worth about four cents per bounding box. Data is the fuel that powers modern technologies run by artificial intelligence engines which is increasingly valuable in today’s industry. High quality labeled data is the most important factor in producing accurate machine learning models which can be used to make powerful predictions and identify patterns humans may not see. Acquiring high quality labeled data however, can be expensive and time consuming. For small companies, academic researchers, or machine learning hobbyists, gathering large datasets for a specific task that …

Detecting Crispr Arrays Using Long-Short Term Memory Network, Shantanu Deshmukh

Master's Projects

CRISPR (Clustered Regularly Interspaced Short Palindromic Repeat) is a se- quence found in the DNA sequence of an organism. It provides provides immunity to the organism. Recently, it was found that the CRISPR-based immunity mechanism can be manipulated to perform genome editing. The problem is, it is hard to know the specificity of this system and in turn, making it highly specific is difficult. More re- search is required to improve this CRISPR-based genome editing. Detecting CRISPR arrays in the DNA sequence is the first step towards this research. In this work, a CRISPR array detection pipeline, CRISPRLstm, is proposed. …

Music Mood Classification Using Convolutional Neural Networks, Revanth Akella

Master's Projects

Grouping music into moods is useful as music is migrating from to online streaming services as it can help in recommendations. To establish the connection between music and mood we develop an end-to-end, open source approach for mood classification using lyrics. We develop a pipeline for tag extraction, lyric extraction, and establishing classification models for classifying music into moods. We investigate techniques to classify music into moods using lyrics and audio features. Using various natural language processing methods with machine learning and deep learning we perform a comparative study across different classification and mood models. The results infer that features …

Fast High Resolution Image Completion, Chinmay Mishra

Master's Projects

This paper presents a method for image completion, an active research area in the field of computer vision. The method described in the paper aims at achieving comparable results to other state of the art methods with approximately four and a half times reduction in training time. It is a two step procedure which involves image completion and enhancing the resolution of the completed image. We use the SSIM metric to evaluate the quality of the completed image and to also time our model against other image completion models.

Detection Of Sand Boils From Images Using Machine Learning Approaches, Aditi S. Kuchi

LSU New Orleans Theses and Dissertations

Levees provide protection for vast amounts of commercial and residential properties. However, these structures degrade over time, due to the impact of severe weather, sand boils, subsidence of land, seepage, etc. In this research, we focus on detecting sand boils. Sand boils occur when water under pressure wells up to the surface through a bed of sand. These make levees especially vulnerable. Object detection is a good approach to confirm the presence of sand boils from satellite or drone imagery, which can be utilized to assist in the automated levee monitoring methodology. Since sand boils have distinct features, applying object …

Sql Injection Detection Using Machine Learning, Sonali Mishra

Master's Projects

Sharing information over the Internet over multiple platforms and web-applications has become a quite common phenomenon in the recent times. The web-based applications that accept critical information from users store this information in databases. These applications and the databases connected to them are susceptible to all kinds of information security threats due to being accessible through the Internet. The threats include attacks such as Cross Side Scripting (CSS), Denial of Service Attack (DoS0, and Structured Query Language (SQL) Injection attacks. SQL Injection attacks fall under the top ten vulnerabilities when we talk about web-based applications. Through this kind of attack, …

Poriferal Vision, Saketh Saxena

Master's Projects

Sponges provide nourishment as well as a habitat for various aquatic organisms. Anatomically, sponges are made up of soft tissue with a silica based exoskeleton which serves both as support and protection for the underlying tissue. The exoskeleton persists after the tissue decomposes, and microscopic parts of the exoskeleton break away to form spicules. Oceanographic studies have shown that the density of the sponge spicules is a good indicator of the sponge population in an area. This measure can be used to study sponge population dynamics over time. The spicule density is measured by imaging spicules from samples of water …

Using Computer Vision To Quantify Coral Reef Biodiversity, Niket Bhodia

Master's Projects

The preservation of the world’s oceans is crucial to human survival on this planet, yet we know too little to begin to understand anthropogenic impacts on marine life. This is especially true for coral reefs, which are the most diverse marine habitat per unit area (if not overall) as well as the most sensitive. To address this gap in knowledge, simple field devices called autonomous reef monitoring structures (ARMS) have been developed, which provide standardized samples of life from these complex ecosystems. ARMS have now become successful to the point that the amount of data collected through them has outstripped …

Over Speed Detection Using Artificial Intelligence, Samkit Patira

Master's Projects

Over speeding is one of the most common traffic violations. Around 41 million people are issued speeding tickets each year in USA i.e one every second. Existing approaches to detect over- speeding are not scalable and require manual efforts. In this project, by the use of computer vision and artificial intelligence, I have tried to detect over speeding and report the violation to the law enforcement officer. It was observed that when predictions are done using YoloV3, we get the best results.

Robust Lightweight Object Detection, Siddharth Kumar

Master's Projects

Object detection is a very challenging problem in computer vision and has been a prominent subject of research for nearly three decades. There has been a promising in- crease in the accuracy and performance of object detectors ever since deep convolutional networks (CNN) were introduced. CNNs can be trained on large datasets made of high resolution images without flattening them, thereby using the spatial information. Their superior learning ability also makes them ideal for image classification and object de- tection tasks. Unfortunately, this power comes at the big cost of compute and memory. For instance, the Faster R-CNN detector required …

Deep Learning Based Real Time Devanagari Character Recognition, Aseem Chhabra

Master's Projects

The revolutionization of the technology behind optical character recognition (OCR) has helped it to become one of those technologies that have found plenty of uses in the entire industrial space. Today, the OCR is available for several languages and have the capability to recognize the characters in real time, but there are some languages for which this technology has not developed much. All these advancements have been possible because of the introduction of concepts like artificial intelligence and deep learning. Deep Neural Networks have proven to be the best choice when it comes to a task involving recognition. There are …

Predicting Off-Target Potential Of Crispr-Cas9 Single Guide Rna, Ishita Mathur

Master's Projects

With advancements in the field of genome engineering, researchers have come up with potential ways for site-specific gene editing. One of the methods uses the Clustered Regularly Interspaced Short Palindromic Repeats - CRISPR-Cas technology. It consists of a Cas9 nuclease and a single guide RNA (sgRNA) that cleaves the DNA at the intended target site. However, the target genome could contain multiple potential off-target sites and cleaving an off-target site can have deleterious effects in case of gene editing in humans.

Lab based assays have been developed to test the off-target effects of guide RNAs. However, it is not feasible …

Deep Learning On Graphs Using Graph Convolutional Networks, Saurabh Mithe

Master's Projects

Graphs are a powerful way to model network data with the objects as nodes and the relationship between the various objects as links. Such graphs contain a plethora of valuable information about the underlying data which can be extracted, analyzed, and visualized using Machine Learning (ML). The challenge to this task is that graphs are non-Euclidean structures which means that they cannot be directly used with ML techniques because ML techniques only work with Euclidean structures like grids or sequences. In order to overcome this challenge, the graph structure first needs to be encoded into an equivalent Euclidean representation in …

Glovenor - Global Vectors For Node Representations, Shishir Kulkarni

Master's Projects

A graph is a very powerful abstract data type that can be used to model entities (nodes) and relationships (edges). Many real world networks like biological, computer and friendship networks can be represented as graphs. Graphs can be mined to extract interesting patterns and interactions between the participating entities. Recently, various Artificial Intelligence (AI) and Machine Learning (ML) techniques are used for this purpose. In order to do that, the nodes of a graph have to be represented as low dimensional feature vectors. Node embedding is the process of generating a �-dimensional feature vector corresponding to each node of a …

Learning To Play The Trading Game, Neeraj Kulkarni

Master's Projects

Can we train a stock trading bot that can take decisions in high-entropy envi- ronments like stock markets to generate profits based on some optimal policy? Can we further extend this learning for any general trading problem? Quantitative Al- gorithms are responsible for more than 75% of the stock trading around the world. Creating a stock market prediction model is comparatively easy. But creating a prof- itable prediction model is still considered as a challenging task in the field of machine learning and deep learning due to the unpredictability of the financial markets. Us- ing biologically inspired computing techniques of …

Graph Classification Using Machine Learning Algorithms, Monica Golahalli Seenappa

Master's Projects

In the Graph classification problem, given is a family of graphs and a group of different categories, and we aim to classify all the graphs (of the family) into the given categories. Earlier approaches, such as graph kernels and graph embedding techniques have focused on extracting certain features by processing the entire graph. However, real world graphs are complex and noisy and these traditional approaches are computationally intensive. With the introduction of the deep learning framework, there have been numerous attempts to create more efficient classification approaches.

For this project, we will be focusing on modifying an existing kernel graph …

Tsar : A System For Defending Hate Speech Detection Models Against Adversaries, Brian Tuan Khieu

Master's Projects

Although current state-of-the-art hate speech detection models achieve praiseworthy results, these models have shown themselves to be vulnerable to attack. Easy to execute lexical manipulations such as the removal of whitespace from a given text create significant issues for word-based hate speech detection models. In this paper, we reproduce the results of five cutting edge models as well as four significant evasion schemes from prior work. Only a limited amount of evasion schemes that also maintain readability exists, and this works to our advantage in the recreation of the original data. Furthermore, we demonstrate that each lexical attack or evasion …

On Adversarial Attacks On Deep Learning Models, Nag Mani

Master's Projects

With recent advancements in the field of artificial intelligence, deep learning has created a niche in the technology space and is being actively used in autonomous and IoT systems globally. Unfortunately, these deep learning models have become susceptible to adversarial attacks which can severely impact their integrity. Research has shown that many state-of-the-art models are vulnerable to attacks by well-crafted adversarial examples. These adversarial examples are perturbed versions of clean data which have small amount of noise added to them. These adversarial samples are imperceptible to the human eye but can easily fool the targeted model. The exposed vulnerabilities of …

Benchmarking Optimization Algorithms For Capacitated Vehicle Routing Problems, Pratik Surana

Master's Projects

The Vehicle Routing Problem (VRP) originated in the 1950s when algorithms and mathematical approaches were applied to find solutions for routing vehicles. Since then, there has been extensive research in the field of VRPs to solve real-life problems. The process of generating an optimal routing schedule for a VRP is complex due to two reasons. First, VRP is considered to be an NP-Hard problem. Second, there are several constraints involved, such as the number of available vehicles, the vehicle capacities, time-windows for pickup or delivery etc.

The main goal for this project was to compare different optimization algorithms for solving …

Intelligent Log Analysis For Anomaly Detection, Steven Yen

Master's Projects

Computer logs are a rich source of information that can be analyzed to detect various issues. The large volumes of logs limit the effectiveness of manual approaches to log analysis. The earliest automated log analysis tools take a rule-based approach, which can only detect known issues with existing rules. On the other hand, anomaly detection approaches can detect new or unknown issues. This is achieved by looking for unusual behavior different from the norm, often utilizing machine learning (ML) or deep learning (DL) models. In this project, we evaluated various ML and DL techniques used for log anomaly detection. We …