no code implementations • 8 Mar 2024 • Anupam Chaudhuri, Anj Simmons, Mohamed Abdelrazek
This paper presents our experiments to quantify the manifolds learned by ML models (in our experiment, we use a GAN model) as they train.
1 code implementation • 22 Nov 2023 • Andres Pollano, Anupam Chaudhuri, Anj Simmons
We attempt to detect out-of-distribution (OOD) text samples though applying Topological Data Analysis (TDA) to attention maps in transformer-based language models.
1 code implementation • 4 Jul 2023 • Anj Simmons, Rajesh Vasa
This paper proposes exploiting the common sense knowledge learned by large language models to perform zero-shot reasoning about crimes given textual descriptions of surveillance videos.
no code implementations • 26 May 2023 • Jai Kannan, Scott Barnett, Anj Simmons, Taylan Selvi, Luis Cruz
Deep learning models have become essential in software engineering, enabling intelligent features like image captioning and document generation.
no code implementations • 20 Sep 2022 • Tuan Dung Lai, Anj Simmons, Scott Barnett, Jean-Guy Schneider, Rajesh Vasa
Objective: Our objective is to investigate whether there is a discrepancy in the distribution of resolution time between ML and non-ML issues and whether certain categories of ML issues require a longer time to resolve based on real issue reports in open-source applied ML projects.
no code implementations • 11 Aug 2022 • Anj Simmons, Rajesh Vasa, Antonio Giardina
This paper demonstrates our vision for knowledge graphs that assist machines to reason about the cause of signals observed by sensors.
1 code implementation • 24 Jun 2022 • Anj Simmons, Rajesh Vasa
This paper presents an knowledge graph to assist in reasoning over signals for intelligence purposes.
no code implementations • 8 May 2022 • Jai Kannan, Scott Barnett, Luís Cruz, Anj Simmons, Akash Agarwal
In our approach we attempt to resolve this problem by exploring the use of context which includes i) purpose of the source code, ii) technical domain, iii) problem domain, iv) team norms, v) operational environment, and vi) development lifecycle stage to provide contextualised error reporting for code analysis.
1 code implementation • 18 Feb 2022 • Anj Simmons
We present a reliability measure for smart surveillance systems, taking into account the adversarial nature of intrusion.