N
Nathan Hilliard
Researcher at Stetson University
Publications - 8
Citations - 188
Nathan Hilliard is an academic researcher from Stetson University. The author has contributed to research in topics: User experience design & User interface. The author has an hindex of 4, co-authored 8 publications receiving 140 citations. Previous affiliations of Nathan Hilliard include Pacific Northwest National Laboratory.
Papers
More filters
Posted Content
Few-Shot Learning with Metric-Agnostic Conditional Embeddings
Nathan Hilliard,Lawrence Phillips,Scott Howland,Artëm Yankov,Courtney D. Corley,Nathan O. Hodas +5 more
TL;DR: This work introduces a novel architecture where class representations are conditioned for each few-shot trial based on a target image, and deviates from traditional metric-learning approaches by training a network to perform comparisons between classes rather than relying on a static metric comparison.
Posted Content
Faster Fuzzing: Reinitialization with Deep Neural Models
TL;DR: Using GAN shows promise as a reinitialization strategy for AFL to help the fuzzer exercise deep paths in software and out-performed a random augmentation strategy, as measured by the number of unique code paths discovered.
Proceedings ArticleDOI
SHARKZOR: Human in the Loop ML for User-Defined Image Classification
TL;DR: A human in the loop system with interactions focusing on 3 main user tasks that approximates the user's mental model and automates organization of the entire dataset in Sharkzor.
Posted Content
Sharkzor: Interactive Deep Learning for Image Triage, Sort and Summary
Meg Pirrung,Nathan Hilliard,Artëm Yankov,Nancy O'Brien,Paul Weidert,Courtney D. Corley,Nathan O. Hodas +6 more
TL;DR: Sharkzor is a web application for machine-learning assisted image sort and summary that leverages deep learning algorithms to infer, augment, and automate the user's mental model.
Posted Content
Dynamic Input Structure and Network Assembly for Few-Shot Learning
TL;DR: This paper describes an approach to constructing and training a network that can handle arbitrary example sizes dynamically as the system is used, making it impractical for production systems where class sizes can vary.