Index Catalog // ScholarsArchive@OSU

On Avoiding Power-Seeking by Artificial Intelligence

Creator:: Turner, Alexander M.
Abstract:: We do not know how to align a very intelligent AI agent's behavior with human interests. I investigate whether—absent a full solution to this AI alignment problem—we can build smart {\ai} agents which have limited impact on the world, and which do not autonomously seek power. In this thesis, I...
Resource Type:: Dissertation
Full Text:: AN ABSTRACT OF THE DISSERTATION OF Alexander

Active Learning from Examples, Queries and Explanations

Creator:: Hamidi-Haines, Mandana
Abstract:: Humans are remarkably efficient in learning by interacting with other people and observing their behavior. Children learn by watching their parents’ actions and mimic their behavior. When they are not sure about their parents demonstration, they communicate with them, ask questions, and learn from their feedback. On the other hand,...
Resource Type:: Dissertation

Video Analysis : Techniques for Semi-Supervised Video Object Instance Segmentation and Tracking-by-Detection in the Wild

Creator:: Firl, Alrik K.
Abstract:: This thesis consists of two major components. The first part is concerned with video object instance segmentation (VOS), which is the task of assigning per-pixel labels perframe of a video sequence to indicate foreground object instance membership, given the first frame ground truth mask. VOS has myriad applications, from video...
Resource Type:: Masters Thesis

Re-understanding Finite-State Representations of Recurrent Policy Networks

Creator:: Danesh, Mohamad H.
Abstract:: We propose an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this problem by transforming such recurrent policy networks into finite-state machines (FSM) and then analyzing the equivalent minimized FSM. While this led to interesting insights, the minimization process can obscure a deeper understanding...
Resource Type:: Masters Thesis

Fine-Grained Object Recognition Under Limited Training Data

Creator:: Lam, Michael Q.
Abstract:: This dissertation addresses object recognition in challenging settings, where distinct object classes are visually very similar (e.g., species of birds and insects) and/or access to training examples of object classes is limited (e.g., due to the associated high costs of data annotation). In this dissertation, we present a variety of...
Resource Type:: Dissertation

Auxiliary Tasks for Efficient Learning of Point-Goal Navigation

Creator:: Desai, Saurabh Satish
Abstract:: Top-performing approaches to embodied AI tasks like point-goal navigation often rely on training agents via reinforcement learning over tens of millions (or even billions) of experiential steps – learning neural agents that map directly from visual observations to actions. In this work, we question whether these extreme training durations are...
Resource Type:: Masters Thesis

Bayesian optimization with empirical constraints

Creator:: Azimi, Javad
Abstract:: Bayesian Optimization (BO) methods are often used to optimize an unknown function f(•) that is costly to evaluate. They typically work in an iterative manner. In each iteration, given a set of observation points, BO algorithms select k ≥ 1 points to be evaluated. The results of those points are...
Resource Type:: Dissertation

How to Debug Inclusivity Bugs? An Empirical Investigation of Finding-to-Fixing with Information Architecture

Creator:: Guizani, Mariam, Steinmacher, Igor, Emard, Jillian, Fallatah, Abrar, Burnett, Margaret, and Sarma, Anita
Abstract:: Background: Although some previous research has found ways to find inclusivity bugs (biases in software that introduce inequities among cognitively diverse individuals), little attention has been paid to how to go about fixing such bugs. We hypothesized that Information Architecture (IA)--the way information is organized, structured and labeled--may provide the...
Resource Type:: Research Paper

Visual object discovery and understanding

Creator:: Yuan, Jialin
Abstract:: Learning to recognize objects is a fundamental and essential step in human perception and understanding of the world. Accordingly, research of object discovery across diverse modalities plays a pivotal role in the context of computer vision. This field not only contributes significantly to enhancing our understanding of visual information but...
Resource Type:: Dissertation

A Structural Theorem For Shortest Vertex-Disjoint Paths Computation in Planar Graphs

Creator:: Zafarani, Farzad
Abstract:: Given k terminal pairs (s₁,t₁),(s₂,t₂),..., (s[subscript k],t[subscript k]) in an edge-weighted graph G, the k Shortest Vertex-Disjoint Paths problem is to find a collection P₁, P₂,..., P[subscript k] of vertex-disjoint paths with minimum total length, where P[subscript i] is an s[subscript i]-to-t[subscript i] path. As a special case of the...
Resource Type:: Masters Thesis
Full Text:: . Journal of Computer and System Sciences, 67(3):473–496, 2003. [13] Joel Hass and Peter Scott

ScholarsArchive@OSU

On Avoiding Power-Seeking by Artificial Intelligence

Active Learning from Examples, Queries and Explanations

Video Analysis : Techniques for Semi-Supervised Video Object Instance Segmentation and Tracking-by-Detection in the Wild

Re-understanding Finite-State Representations of Recurrent Policy Networks

Fine-Grained Object Recognition Under Limited Training Data

Auxiliary Tasks for Efficient Learning of Point-Goal Navigation

Bayesian optimization with empirical constraints

How to Debug Inclusivity Bugs? An Empirical Investigation of Finding-to-Fixing with Information Architecture

Visual object discovery and understanding

A Structural Theorem For Shortest Vertex-Disjoint Paths Computation in Planar Graphs

Limit your search

Academic Affiliation

Advisor

Commencement Year

Committee Member

Creator

Contributor

Date

Decade

Degree Field

Degree Level

Degree Name

File Format

Language

License

Non-Academic Affiliation

Peer Reviewed

Resource Type

Rights Statement

Subject

Search Constraints

Search Results

Limit your search