7 citations · 12 across the 6 of their papers we have counts for
4 papers · 1 filter
Adaptive Estimation and Learning under Temporal Distribution Shift
Dheeraj Baby, Yifei Tang, Hieu Duy Nguyen +2
In this paper, we study the problem of estimation and learning under temporal distribution shift. Consider an observation sequence of length , which is a noisy realization of a…
Accelerator-Aware Training for Transducer-Based Speech Recognition
Suhaila M. Shakiah, Rupak Vignesh Swaminathan, Hieu Duy Nguyen +6
Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network a…
Optimal N-ary ECOC Matrices for Ensemble Classification
Hieu D. Nguyen, Lucas J. Lavalva, Shen-Shyang Ho +2
A new recursive construction of -ary error-correcting output code (ECOC) matrices for ensemble classification methods is presented, generalizing the classic doubling constructio…
Ensemble Learning using Error Correcting Output Codes: New Classification Error Bounds
Hieu D. Nguyen, Mohammed Sarosh Khan, Nicholas Kaegi +4
New bounds on classification error rates for the error-correcting output code (ECOC) approach in machine learning are presented. These bounds have exponential decay complexity with…