Jokin Labaien
Research Subjects
Jokin Labaien has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Ekhi Zugasti
IK4-Ikerlan
2 shared publications - Tsuyoshi Idé
IBM T. J. Watson Research Center USA
2 shared publications - Xabier De Carlos
IK4-Ikerlan Research Center
2 shared publications Ekhi Zugasti
1 shared publicationPin-Yu Chen
1 shared publication- Pin-Yu Chen
IBM Research, Yorktown Heights, New York, USA
1 shared publication
Latest Publications
- Open Access
Improving Transformers using Faithful Positional Encoding
We propose a new positional encoding method for a neural network architecture called the Transformer. Unlike the standard sinusoidal positional encoding, our approach is based on solid mathematical grounds and has a guarantee of not losing information about the positional order of the input sequence. We show that the new encoding approach systematically improves the prediction performance in the time-series classification task.
Open AccessImproving Transformers using Faithful Positional Encoding
We propose a new positional encoding method for a neural network architecture called the Transformer. Unlike the standard sinusoidal positional encoding, our approach is based on solid mathematical grounds and has a guarantee of not losing information about the positional order of the input sequence. We show that the new encoding approach systematically improves the prediction performance in the time-series classification task.
- 19 May 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 274
Diagnostic spatio-temporal transformer with faithful encoding
- 19 May 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 274
Diagnostic spatio-temporal transformer with faithful encoding
- Open Access
- 24 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (5) , 2912
Real-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using Autoencoders
Explainable Artificial Intelligence (XAI) has gained significant attention in recent years due to concerns over the lack of interpretability of Deep Learning models, which hinders their decision-making processes. To address this issue, counterfactual explanations have been proposed to elucidate the reasoning behind a model’s decisions by providing what-if statements as explanations. However, generating counterfactuals traditionally involves solving an optimization problem for each input, making it impractical for real-time feedback. Moreover, counterfactuals must meet specific criteria, including being user-driven, causing minimal changes, and staying within the data distribution. To overcome these challenges, a novel model-agnostic approach called Real-Time Guided Counterfactual Explanations (RTGCEx) is proposed. This approach utilizes autoencoders to generate real-time counterfactual explanations that adhere to these criteria by optimizing a multiobjective loss function. The performance of RTGCEx has been evaluated on two datasets: MNIST and Gearbox, a synthetic time series dataset. The results demonstrate that RTGCEx outperforms traditional methods in terms of speed and efficacy on MNIST, while also effectively identifying and rectifying anomalies in the Gearbox dataset, highlighting its versatility across different scenarios.
- 24 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (5) , 2912
Open AccessReal-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using Autoencoders
Explainable Artificial Intelligence (XAI) has gained significant attention in recent years due to concerns over the lack of interpretability of Deep Learning models, which hinders their decision-making processes. To address this issue, counterfactual explanations have been proposed to elucidate the reasoning behind a model’s decisions by providing what-if statements as explanations. However, generating counterfactuals traditionally involves solving an optimization problem for each input, making it impractical for real-time feedback. Moreover, counterfactuals must meet specific criteria, including being user-driven, causing minimal changes, and staying within the data distribution. To overcome these challenges, a novel model-agnostic approach called Real-Time Guided Counterfactual Explanations (RTGCEx) is proposed. This approach utilizes autoencoders to generate real-time counterfactual explanations that adhere to these criteria by optimizing a multiobjective loss function. The performance of RTGCEx has been evaluated on two datasets: MNIST and Gearbox, a synthetic time series dataset. The results demonstrate that RTGCEx outperforms traditional methods in terms of speed and efficacy on MNIST, while also effectively identifying and rectifying anomalies in the Gearbox dataset, highlighting its versatility across different scenarios.
- 11 September 2020
- Published by Springer Nature
- p. 235-244
Contrastive Explanations for a Deep Learning Model on Time-Series Data
- 11 September 2020
- Published by Springer Nature
- p. 235-244
Contrastive Explanations for a Deep Learning Model on Time-Series Data