Emel Ay

Papers

Total Citations

H-Index

About

Emel Ay is a researcher at the forefront of applying deep learning to time series analysis, with a particular focus on model efficiency and knowledge transfer. Her most-cited work, "A study of Knowledge Distillation in Fully Convolutional Network for Time Series Classification" (2022, 14 citations), addresses a critical challenge in modern machine learning: how to compress complex deep learning models without sacrificing performance. By pioneering the application of knowledge distillation—a technique more commonly used in computer vision—to fully convolutional networks for time series classification, Ay has opened new pathways for deploying sophisticated models in resource-constrained environments. Her research bridges the gap between state-of-the-art deep learning architectures and practical, real-world applications where computational efficiency is paramount. This work has been recognized as a significant contribution to the growing field of efficient deep learning for temporal data, earning attention from researchers working on model compression, edge computing, and IoT applications. Ay's innovative approach demonstrates how techniques from one domain can be successfully adapted to solve pressing challenges in another, making her a notable voice in the ongoing evolution of deep learning methodologies.