Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Co-Planar Stereotaxic Atlas of the Human Brain—3-Dimensional Proportional System: An Approach to Cerebral Imaging, J. Talairach, P. Tournoux. Georg Thieme Verlag, New York (1988), 122 pp., 130 figs. DM 268

The power of feedback.

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

In this paper we review classification algorithms used to design brain–computer interface (BCI) systems based on electroencephalography (EEG). We briefly present the commonly employed algorithms and describe their critical properties. Based on the literature, we compare them in terms of performance and provide guidelines to choose the suitable classification algorithm(s) for a specific BCI.

/pdf/a-review-of-classification-algorithms-for-eeg-based-brain-p1h22hb1wr.pdf

A review of classification algorithms for EEG-based brain–computer interfaces

While recent research on Brain-Computer Interfaces (BCI) has highlighted their potential for many applications, they remain barely used in practice, outside laboratories. The main reason is their lack of reliability and robustness. Indeed, with current BCI, mental state recognition is usually slow and too often incorrect. These poor performances are due in part to the EEG signal processing algorithms used since they are not yet able to deal appropriately with their noisy, complex and non-stationary nature. However, there is another component of the BCI loop that may also be deficient: the user him/herself who may not be able to produce reliable EEG patterns. Indeed, it is widely acknowledged that "BCI use is a skill" [1], which means the user must be properly trained to be able to successfully use the BCI. If the BCI user is indeed unable to correctly perform the desired mental commands, whatever the signal processing algorithms used, there would be no way to properly identify them. Despite this, the BCI community has focused the majority of its research effort on signal processing and machine learning, mostly neglecting the human in the loop. In this work, we argue that the user is one of the most critical components of the BCI loop that may explain the limited reliability of current BCI. It does not mean that BCI users are per se poor performers or incompetent. It means that the way current BCI training protocols are designed is inappropriate, making BCI users unable to properly learn and use the BCI skill.

https://hal.inria.fr/hal-00834391/document

On the need for alternative feedback training approaches for BCI

While being very promising, brain-computer interfaces (BCI) remain barely used outside laboratories because they are not reliable enough. It has been suggested that current training approaches may be partly responsible for the poor reliability of BCIs as they do not satisfy recommendations from psychology and are thus inadequate. To determine to which extent such BCI training approaches (i.e., feedback and training tasks) are suitable to learn a skill, we used them in another context (without a BCI) to train 20 users to perform simple motor tasks. While such approaches enabled learning for most subjects, results also showed that 15% of them were unable to learn these simple motor tasks, which is close to the BCI illiteracy rate [1]. This further suggests that current BCI training approaches may be an important factor of illiteracy, thus deserving more attention.

https://hal.inria.fr/hal-01052692/document

How Well Can We Learn With Standard BCI Training Approaches? A Pilot Study.

While often presented as promising assistive technologies for motor-impaired users, electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs) remain barely used outside laboratories due to low reliability in real-life conditions. There is thus a need to design long-term reliable BCIs that can be used outside-of-the-lab by end-users, e.g., severely motor-impaired ones. Therefore, we propose and evaluate the design of a multi-class Mental Task (MT)-based BCI for longitudinal training (20 sessions over 3 months) of a tetraplegic user for the CYBATHLON BCI series 2019. In this BCI championship, tetraplegic pilots are mentally driving a virtual car in a racing video game. We aimed at combining a progressive user MT-BCI training with a newly designed machine learning pipeline based on adaptive Riemannian classifiers shown to be promising for real-life applications. We followed a two step training process: the first 11 sessions served to train the user to control a 2-class MT-BCI by performing either two cognitive tasks (REST and MENTAL SUBTRACTION) or two motor-imagery tasks (LEFT-HAND and RIGHT-HAND). The second training step (9 remaining sessions) applied an adaptive, session-independent Riemannian classifier that combined all 4 MT classes used before. Moreover, as our Riemannian classifier was incrementally updated in an unsupervised way it would capture both within and between-session non-stationarity. Experimental evidences confirm the effectiveness of this approach. Namely, the classification accuracy improved by about 30% at the end of the training compared to initial sessions. We also studied the neural correlates of this performance improvement. Using a newly proposed BCI user learning metric, we could show our user learned to improve his BCI control by producing EEG signals matching increasingly more the BCI classifier training data distribution, rather than by improving his EEG class discrimination. However, the resulting improvement was effective only on synchronous (cue-based) BCI and it did not translate into improved CYBATHLON BCI game performances. For the sake of overcoming this in the future, we unveil possible reasons for these limited gaming performances and identify a number of promising future research directions. Importantly, we also report on the evolution of the user's neurophysiological patterns and user experience throughout the BCI training and competition.

/pdf/long-term-bci-training-of-a-tetraplegic-user-adaptive-2qwtmwotfa.pdf

Long-Term BCI Training of a Tetraplegic User: Adaptive Riemannian Classifiers and User Training.

This chapter aims at providing the reader with two examples of open-source BCI-games that work with the OpenViBE platform. These two games are “Brain Invaders” and “Use-The-Force!” and are representative examples of two types of BCI: ERP-based BCI and oscillatory activity-based BCI. This chapter presents the principle, design and evaluation of these games, as well as how they are implemented in practice within OpenViBE. This aims at providing the interested readers with a practical basis to design their own BCI-based games.

/pdf/recreational-applications-of-openvibe-brain-invaders-and-use-22e5xy88y4.pdf

Recreational Applications of OpenViBE: Brain Invaders and Use-the-Force

Despite their potential for many applications, Brain -- Computer Interfaces (BCI) are still rarely used due to their low reliability and long training. These limitations are partly due to inappropriate training protocols, which includes the feedback provided to the user. While feedback should theoretically be explanatory, motivating and meaningful, current BCI feedback is usually boring, corrective only and difficult to understand. In this study, different features of the electroencephalogram signals were explored to be used as a richer, explanatory BCI feedback. First, based on offline mental imagery BCI data, muscular relaxation was notably found to be negatively correlated to BCI performance. Second, this study reports on an online BCI evaluation using muscular relaxation as additional feedback. While this additional feedback did not lead to significant change in BCI performance, this study showed that multiple feedbacks can be used without deteriorating performance and provided interesting insights for explanatory BCI feedback design.

/pdf/towards-explanatory-feedback-for-user-training-in-brain-25fnvz4ekp.pdf

Fabien Lotte

Papers

On the need for alternative feedback training approaches for BCI

How Well Can We Learn With Standard BCI Training Approaches? A Pilot Study.

Long-Term BCI Training of a Tetraplegic User: Adaptive Riemannian Classifiers and User Training.

Recreational Applications of OpenViBE: Brain Invaders and Use-the-Force

Towards Explanatory Feedback for User Training in Brain-Computer Interfaces