Automating Custom Loss Functions in Deep Learning

Designing and training deep learning models often requires advanced expertise, particularly when defining loss functions, optimizers, and model architectures. This work explored how large language models could lower those barriers by automating the creation of custom loss functions tailored to specific optimization goals. The capstone was presented at the Graduate Poster Exhibition during the 2025… continue reading

Five-Year, $700,000 Award Supports Women in STEM

For women pursuing careers in science and mathematics, sustained mentorship, faculty leadership, and institutional investment are often decisive in whether opportunity leads to long-term participation. At Rutgers University–Camden, a new five-year, $700,000 award from the Henry Luce Foundation’s Clare Boothe Luce Program for Women in STEM will support professorships and initiatives designed to strengthen those… continue reading

What It Takes to Turn an AI Pilot Into Lasting Impact

Artificial Intelligence (AI) pilots get launched every day, but very few make it past the novelty stage. That tension is where this reflection begins. Data Science MS alum Eshaa Gogia, now a Data Engineer at Florida Blue in the Miami and Fort Lauderdale area, lays out why so many promising ideas never become scalable change…. continue reading

From Code to Care: A Vision for Data-Driven Healthcare

Originally from Andhra Pradesh, India, Geetanjali Kaza is a graduate student in Data Science at Rutgers University-Camden. With a Bachelor’s degree in Computer Science and Engineering and valuable work experience, she is dedicated to developing innovative methods for extracting meaningful insights from vast healthcare datasets. Her academic journey is driven by a passion for leveraging… continue reading

Using Deep Learning to Predict Brain Aging from MRI Scans

Eshaa Gogia, an alum of the Data Science MS program at Rutgers–Camden, and Iman Dehzangi, assistant professor in the Department of Computer Science, coauthored a new study with Arash Dehzangi. Their article, “Automated Subregional Hippocampus Segmentation Using 3D CNNs: A Computational Framework for Brain Aging Biomarker Analysis,” was published in Algorithms as part of a… continue reading

Transforming Ed Data into Actionable Insights

Turning raw educational data into meaningful insights requires more than just technical expertise—it takes a strategic approach to analytics. Nihil Kottal, a Data Science MS student at Rutgers Graduate School-Camden, has developed EduMetric Solutions, a Power BI tool designed to streamline data analysis in higher education. By integrating datasets from the Bureau of Labor Statistics,… continue reading