11 papers
JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching
Mohammed Alsakabi, Kejia Hu, John M. Dolan +1
Existing implicit neural representation (INR) approaches suffer from stochastic initialization that does not guarantee consistent or high-quality performance across runs, with vari…
FM-SIREN & FM-FINER: Implicit Neural Representation Using Nyquist-based Orthogonality
Mohammed Alsakabi, Wael Mobeirek, John M. Dolan +1
Existing periodic activation-based implicit neural representation (INR) networks, such as SIREN and FINER, suffer from hidden feature redundancy, where neurons within a layer captu…
Reproducing and Extending RaDelft 4D Radar with Camera-Assisted Labels
Kejia Hu, Mohammed Alsakabi, John M. Dolan +1
Recent advances in 4D radar highlight its potential for robust environment perception under adverse conditions, yet progress in radar semantic segmentation remains constrained by t…
Quantifying Distribution Shift in Traffic Signal Control with Histogram-Based GEH Distance
Federico Taschin, Ozan K. Tonguz
Traffic signal control algorithms are vulnerable to distribution shift, where performance degrades under traffic conditions that differ from those seen during design or training. T…
CFL: On the Use of Characteristic Function Loss for Domain Alignment in Machine Learning
Abdullah Almansour, Ozan Tonguz
Machine Learning (ML) models are extensively used in various applications due to their significant advantages over traditional learning methods. However, the developed ML models of…
Edge-Based Speech Transcription and Synthesis for Kinyarwanda and Swahili Languages
Pacome Simon Mbonimpa, Diane Tuyizere, Azizuddin Ahmed Biyabani +1
This paper presents a novel framework for speech transcription and synthesis, leveraging edge-cloud parallelism to enhance processing speed and accessibility for Kinyarwanda and Sw…