LipschitzLR: Using theoretically computed adaptive learning rates for fast convergence R Yedida, S Saha, T Prashanth Applied Intelligence, 1-19, 2020 | 54* | 2020 |
On the Value of Oversampling for Deep Learning in Software Defect Prediction R Yedida, T Menzies IEEE Transactions on Software Engineering, 2021 | 49 | 2021 |
Evolution of novel activation functions in neural network training for astronomy data: habitability classification of exoplanets S Saha, N Nagaraj, A Mathur, R Yedida, S HR The European Physical Journal Special Topics 229 (16), 2629-2738, 2020 | 36 | 2020 |
Employee Attrition Prediction R Yedida, R Reddy, R Vahi, R Jana, A GV, D Kulkarni arXiv preprint arXiv:1806.10480, 2018 | 34 | 2018 |
Learning to recognize actionable static code warnings (is intrinsically easy) X Yang, J Chen, R Yedida, Z Yu, T Menzies Empirical Software Engineering 26 (3), 1-24, 2021 | 33* | 2021 |
Simpler hyperparameter optimization for software analytics: Why, how, when? A Agrawal, X Yang, R Agrawal, R Yedida, X Shen, T Menzies IEEE Transactions on Software Engineering 48 (8), 2939-2954, 2021 | 22 | 2021 |
How to improve deep learning for software analytics: (a case study with code smell detection) R Yedida, T Menzies Proceedings of the 19th International Conference on Mining Software …, 2022 | 10 | 2022 |
An expert system for redesigning software for cloud applications R Yedida, R Krishna, A Kalia, T Menzies, J Xiao, M Vukovic Expert Systems with Applications, 2023 | 9* | 2023 |
How to Find Actionable Static Analysis Warnings: A Case Study With FindBugs R Yedida, HJ Kang, H Tu, X Yang, D Lo, T Menzies IEEE Transactions on Software Engineering, 2023 | 9 | 2023 |
Old but Gold: Reconsidering the value of feedforward learners for software analytics R Yedida, X Yang, T Menzies arXiv preprint arXiv:2101.06319, 2021 | 8* | 2021 |
Parsimonious Computing: A Minority Training Regime for Effective Prediction in Large Microarray Expression Data Sets S Sridhar, S Saha, A Shaikh, R Yedida, S Saha 2020 International Joint Conference on Neural Networks (IJCNN), 1-8, 2020 | 8 | 2020 |
Beginning with machine learning: a comprehensive primer R Yedida, S Saha The European Physical Journal Special Topics 230 (10), 2363-2444, 2021 | 6 | 2021 |
Lessons learned from hyper-parameter tuning for microservice candidate identification R Yedida, R Krishna, A Kalia, T Menzies, J Xiao, M Vukovic 2021 36th IEEE/ACM International Conference on Automated Software …, 2021 | 5 | 2021 |
(Re) Use of Research Results (Is Rampant) MT Baldassarre, N Ernst, B Hermann, T Menzies, R Yedida Communications of the ACM 66 (2), 75-81, 2023 | 3* | 2023 |
Documenting evidence of a reuse of ‘a systematic study of the class imbalance problem in convolutional neural networks’ R Yedida, T Menzies Proceedings of the 29th ACM Joint Meeting on European Software Engineering …, 2021 | 1 | 2021 |
Strong convexity-guided hyper-parameter optimization for flatter losses R Yedida, S Saha arXiv preprint arXiv:2402.05025, 2024 | | 2024 |
SMOOTHIE: A Theory of Hyper-parameter Optimization for Software Analytics R Yedida, T Menzies arXiv preprint arXiv:2401.09622, 2024 | | 2024 |
TEXT MINING OF THE PEOPLE’S PHARMACY RADIO SHOW TRANSCRIPTS CAN IDENTIFY NOVEL DRUG REPURPOSING HYPOTHESES R Yedida, JM Beasley, D Korn, SM Abrar, CC Melo-Filho, E Muratov, ... medRxiv, 2022.02. 02.22270107, 2022 | | 2022 |
Documenting evidence of a reuse of ‘on the number of linear regions of deep neural networks’ R Yedida, T Menzies Proceedings of the 29th ACM Joint Meeting on European Software Engineering …, 2021 | | 2021 |
Optimizing Inter-nationality of Journals: A classical gradient approach revisited via Swarm Intelligence L Khaidem, R Yedida, AJ Theophilus Modeling, Machine Learning and Astronomy: First International Conference …, 2020 | | 2020 |