CV
Basics
Name | Aman Malali |
Label | MS/PhD Student |
amalali@umass.edu | |
Url | https://amanmalali.github.io/ |
Summary | PhD student at UMass Amherst working in the field of MLOps, focusing on model maintenance and retraining |
Work
-
09.01 - Present Data systems Research for Exploration, Analytics, and Modeling Lab (DREAM Lab)
University of Massachusetts Amherst
Predictive machine learning (ML) model maintenance
- Currently working on methods to predict model performance without ground truth by utilizing custom ensemble models and uncertainty measures.
- Creating predictive retraining strategies to retrain models with minimal downtime and improved predictive performance on drifting data.
-
06.17 - 09.06 PhD Research Intern
Dolby Advanced Technology Group (ATG)
Extended and improved predictive ML model maintenance
- Developed a dynamic temperature scaling method for machine learning models that calibrates logits based on input features, improving uncertainty estimation and prediction reliability
- Expanded predictive model maintenance by incorporating granular loss levels and adaptive loss bounds to optimize retraining decisions, while experimenting with extensions to address concept drift.
Education
-
09.01 - present Amherst, MA, USA
M.S/PhD Student
University of Massachusetts Amherst
Computer Science
- COMPSCI 683: Artificial Intelligence
- COMPSCI 645: Database Design and Implementation
- COMPSCI 611: Advanced Algorithms
- COMPSCI 682: Neural Networks
Publications
-
Supervised ECG wave segmentation using convolutional LSTM
ICT Express
Malali, A., Hiriyannaiah, S., Siddesh, G. M., Srinivasa, K. G., & Sanjay, N. T. (2020). Supervised ECG wave segmentation using convolutional LSTM. ICT express, 6(3), 166-169.
Languages
English | |
Native speaker |
Hindi | |
Native speaker |
Kannada | |
Fluent |