Nicholas Synovic

ORCID: 0000-0003-0413-4594
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Machine Learning and Data Classification
  • Natural Language Processing Techniques
  • Advanced Database Systems and Queries
  • Semantic Web and Ontologies
  • Image Processing and 3D Reconstruction
  • Web Data Mining and Analysis
  • Software Engineering Research
  • Scientific Computing and Data Management
  • Algorithms and Data Compression
  • Data Mining Algorithms and Applications
  • Adversarial Robustness in Machine Learning
  • Psychology of Social Influence
  • Focus Groups and Qualitative Methods
  • Software Testing and Debugging Techniques
  • Orthopedic Surgery and Rehabilitation
  • Advanced Neural Network Applications
  • Anomaly Detection Techniques and Applications
  • Open Source Software Innovations

Loyola University Chicago
2021-2024

Abstract Context Many engineering organizations are reimplementing and extending deep neural networks from the research community. We describe this process as learning model reengineering. Deep reengineering — reusing, replicating, adapting, enhancing state-of-the-art approaches is challenging for reasons including under-documented reference models, changing requirements, cost of implementation testing. Objective Prior work has characterized challenges development, but yet we know little...

10.1007/s10664-024-10521-0 article EN cc-by Empirical Software Engineering 2024-08-20

Deep neural networks achieve state-of-the-art performance on many tasks, but require increasingly complex architectures and costly training procedures. Engineers can reduce costs by reusing a pre-trained model (PTM) fine-tuning it for their own tasks. To facilitate software reuse, engineers collaborate around hubs, collections of PTMs datasets organized problem domain. Although hubs are now comparable in popularity size to other ecosystems, the associated PTM supply chain has not yet been...

10.1145/3560835.3564547 article EN 2022-11-08

Software metrics capture information about software development processes and products. These support decision-making, e.g., in team management or dependency selection. However, existing tools measure only a snapshot of project. Little attention has been given to enabling engineers reason metric trends over time—longitudinal that give insight process, not just product. In this work, we present PRIME (PRocess MEtrics), tool compute visualize process metrics. The currently-supported include...

10.1145/3551349.3559517 article EN 2022-10-10
Coming Soon ...