Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Artificial Intelligence and Robotics
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Articles 1 - 3 of 3
Full-Text Articles in Physical Sciences and Mathematics
Probing As A Technique To Understand Abstract Spaces, Ashlen A. Plasek
Probing As A Technique To Understand Abstract Spaces, Ashlen A. Plasek
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Machine learning models, while very powerful, have their operation obfuscated behind millions of parameters. This obfuscation can make deriving a human meaningful process from a machine learning model very difficult. However, while the intermediate states of a machine learning model are similarly obfuscated, using probing, we can start to explore looking at possible structure in those intermediate states. Large language models are a prime example of this obfuscation, and probing can begin to allow novel experimentation to be performed.
Lidar Segmentation-Based Adversarial Attacks On Autonomous Vehicles, Blake Johnson
Lidar Segmentation-Based Adversarial Attacks On Autonomous Vehicles, Blake Johnson
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Autonomous vehicles utilizing LiDAR-based 3D perception systems are susceptible to adversarial attacks. This paper focuses on a specific attack scenario that relies on the creation of adversarial point clusters with the intention of fooling the segmentation model utilized by LiDAR into misclassifying point cloud data. This can be translated into the real world with the placement of objects (such as road signs or cardboard) at these adversarial point cluster locations. These locations are generated through an optimization algorithm performed on said adversarial point clusters that are introduced by the attacker.
Applications Of Generative Adversarial Networks In Single Image Datasets, Dylan E. Cramer
Applications Of Generative Adversarial Networks In Single Image Datasets, Dylan E. Cramer
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
One of the main difficulties faced in most generative machine learning models is how much data is required to train it, especially when collecting a large dataset is not feasible. Recently there have been breakthroughs in tackling this issue in SinGAN, with its researchers being able to train a Generative Adversarial Network (GAN) on just a single image with a model that can perform many novel tasks, such as image harmonization. ConSinGAN is a model that builds upon this work by concurrently training several stages in a sequential multi-stage manner while retaining the ability to perform those novel tasks.