Alperen Görmez

Alperen Görmez

I am a Ph.D. student at University of Illinois Chicago, doing research on deep learning. Specifically, I am working on the trade-off between the computational cost and the performance of deep learning models.

Publications

5. A. Görmez and E. Koyuncu, "Class-aware Initialization of Early Exits for Pre-training Large Language Models," in 2nd Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ICML 2024), 2024. [Paper] [Code: coming soon]
4. A. Görmez and E. Koyuncu, "Class Based Thresholding in Early Exit Semantic Segmentation Networks," in IEEE Signal Processing Letters, vol. 31, pp. 1184-1188, 2024. [Paper] [Code: coming soon]
3. A. Görmez and E. Koyuncu, "Dataset Pruning Using Early Exit Networks," ICML Workshop on Localized Learning (LLW), 2023. [Paper] [Poster] [Code: coming soon]
2. A. Görmez and E. Koyuncu, "Pruning Early Exit Networks," 2022 Sparsity in Neural Networks, 2022, doi: 10.48550/arXiv.2207.03644. [Paper] [Poster] [Code: coming soon]
1. A. Görmez, V. R. Dasari and E. Koyuncu, "E2CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning," 2022 International Joint Conference on Neural Networks (IJCNN), 2022, pp. 1-8, doi: 10.1109/IJCNN55064.2022.9891952. [Paper] [Poster] [Code]