Transfer Learning in Brain-Computer Interfaces

By Vinay Jayaram, Morteza Alamgir, Yasemin Altun, Bernhard Schölkopf, Moritz Grosse-Wentrup. IEEE Computational Intelligence Magazine, 2015

444 citations recorded by the source corpus.

The performance of brain-computer interfaces (BCIs) improves with the amount of available training data; the statistical distribution of this data, however, varies across subjects as well as across sessions within individual subjects, limiting the transferability of training data or trained models between them. In this article, we review current transfer learning techniques in BCIs that exploit shared structure between training data of multiple subjects and/or sessions to increase performance. We then present a framework for transfer learning in the context of BCIs that can be applied to any arbitrary feature space, as well as a novel regression estimation method that is specifically designed for the structure of a system based on the electroencephalogram (EEG). We demonstrate the utility of our framework and method on subject-to-subject transfer in a motor-imagery paradigm as well as on session-to-session transfer in one patient diagnosed with amyotrophic lateral sclerosis (ALS), showing that it is able to outperform other comparable methods on an identical dataset.

Subfields: Cellular and Molecular Neuroscience, Cognitive Neuroscience, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/9c0ed142aa4afb27c3f3bbb1f09d1b867edee249

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cellular and Molecular Neuroscience

1. Dongrui Wu
2. He He
3. Christian Jutten
4. Yannick Berthoumieu
5. Paolo Zanini
6. Salem Said
7. Marco Congedo

In Cognitive Neuroscience

1. Dongrui Wu
2. He He
3. Christian Jutten
4. Marco Congedo
5. Yannick Berthoumieu
6. Paolo Zanini
7. Salem Said
8. Zhaoxiang Zhang

In Human-Computer Interaction

1. He He
2. Dongrui Wu
3. Mohammad Rostami
4. Aram Galstyan
5. Serban Stan

Citations in the corpus

• Online and Offline Domain Adaptation for Reducing BCI Calibration Effort (2017, background): “2) Transfer/multitask learning, which uses relevant data from other subjects to help the current subject [19], [46].”
• Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach (2018, background): “For MI-based BCIs, the user needs to imagine the movements of his/her body parts (e.g., hands, feet, and tongue), which causes Manuscript received October 25, 2018; revised January 30, 2019 and April 2, 2019; accepted April 24, 2019.”
• Hierarchical Convolutional Neural Networks for EEG-Based Emotion Recognition (2017, background): “Fourier energy [19] is a choice, but the electric activity at each electrode is not a stationary process over time [20].”
• Transfer Learning: A Riemannian Geometry Framework With Applications to Brain–Computer Interfaces (2018, background): “Some examples of transfer learning applied to BCI problem can be found in [15], [21], [27] and [36].”
• Multisource Transfer Learning for Cross-Subject EEG Emotion Recognition (2020, methodology): “EEG has nonstationary characteristic, and we can view every session a slightly new task [8].”