Physical Sciences and Mathematics Commons^™

Towards Robust Classification In Adversarial Learning Using Bayesian Games, Anna Buhman

UNO Student Research and Creative Activity Fair

A well-trained neural network is very accurate when classifying data into different categories. However, a malicious adversary can fool a neural network through tiny changes to the data, called perturbations, that would not even be detectable to a human. This makes neural networks vulnerable to influence by an attacker. Generative Adversarial Networks (GANs) have been developed as one possible solution to this problem [1]. A GAN consists of two neural networks, a generator and a discriminator. The discriminator tries to learn how to classify data into categories. The generator stands in for the attacker and tries to discover the best …

Extension Of The Ezsmt Software System For Non-Tight Constraint Answer Set Programs, Da Shen

UNO Student Research and Creative Activity Fair

Answer set programming (ASP) is a programming language that plays a critical role in the development of software applications in areas of science, humanities, and industry. Yet, it is faced with some challenges. Therefore, researchers develop a related paradigm called constraint answer set programming (CASP) to tackle several issues of ASP tools. Recently, a method is proposed to find solutions to CASP programs by using satisfiability modulo theories (SMT) solvers. SMT solvers are high-performance systems stemming from the software verification community.

This SMT-based approach is implemented in a system called EZSMT, which often outperforms its peers. Yet, it has several …

Intelligent And Human-Aware Decision Making For Semi-Autonomous Human Rehabilitation Assistance Using Modular Robots, Anoop Mishra

UNO Student Research and Creative Activity Fair

Modular Self-reconfigurable Robots (MSRs) are robots that can adapt their shape and mobility while performing their operations. We are developing an MSR called MARIO (Modular Robots for Assistance in Robust and Intelligent Operations) to assist patients with spinal cord injury in performing daily living tasks. In this research, we are investigating computational techniques that will enable MARIO to autonomously adapt its shape while performing an assistive task, and, while remaining aware of the human user’s satisfaction in receiving assistance from MARIO. We are developing semi-autonomous decision making techniques within a computational framework called shared autonomy that will adapt MARIO’s movements …