Jesus Barreda
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jesus Barreda has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Ashley Gomez
University of Texas Rio Grande Valley, Edinburg, TX, USA
1 shared publication - Kaixiong Zhou
North Carolina State University, Raleigh, NC, USA
1 shared publication - Li Zhang
University of Texas Rio Grande Valley
1 shared publication - Ruben Puga
University of Texas Rio Grande Valley, Edinburg, TX, USA
1 shared publication
Latest Publications
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3622-3626
COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification
Multivariate time series classification is an important task with widespread domains of applications. Recently, deep neural networks (DNN) have achieved state-of-the-art performance in time series classification. However, they often require large expert-labeled training datasets which can be infeasible in practice. In few-shot settings, i.e. only a limited number of samples per class are available in training data, DNNs show a significant drop in testing accuracy and poor generalization ability. In this paper, we propose to address these problems from an optimization and a loss function perspective. Specifically, we propose a new learning framework named COSCO consisting of a sharpness-aware minimization (SAM) optimization and a Prototypical loss function to improve the generalization ability of DNN for multivariate time series classification problems under few-shot setting. Our experiments demonstrate our proposed method outperforms the existing baseline methods. Our source code is available at: https://github.com/JRB9/COSCO.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3622-3626
Open AccessCOSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification
Multivariate time series classification is an important task with widespread domains of applications. Recently, deep neural networks (DNN) have achieved state-of-the-art performance in time series classification. However, they often require large expert-labeled training datasets which can be infeasible in practice. In few-shot settings, i.e. only a limited number of samples per class are available in training data, DNNs show a significant drop in testing accuracy and poor generalization ability. In this paper, we propose to address these problems from an optimization and a loss function perspective. Specifically, we propose a new learning framework named COSCO consisting of a sharpness-aware minimization (SAM) optimization and a Prototypical loss function to improve the generalization ability of DNN for multivariate time series classification problems under few-shot setting. Our experiments demonstrate our proposed method outperforms the existing baseline methods. Our source code is available at: https://github.com/JRB9/COSCO.