News Release

Melding our minds with the outside world

New book shows how science lets our will be done on Earth, just by thinking of it

Book Announcement

World Scientific

Deep Learning for EEG-Based Brain-Computer Interfaces: Representations, Algorithms and Applications

image: Cover for "Deep Learning for EEG-Based Brain-Computer Interfaces: Representations, Algorithms and Applications" view more 

Credit: World Scientific

Affecting the real world just by using the power of spirit sounds like magic—but it isn’t. This can actually be achieved scientifically by decoding human brain signals into computer-recognizable commands, and then using a general computer (such as robot) to implement your will in the physical world. The systems that bridge the human brain and actionable computers are called Brain-Computer Interfaces (BCIs). The bottleneck of up-to-date BCI development, however, is the issue of accurately recognizing the real intention from noisy brain signals. This is why deep learning models are needed: deep learning algorithms provide a convincing solution with their outstanding high-level representation learning ability.

Deep Learning for EEG-Based Brain-Computer Interfaces shows how the emerging work in deep learning helps address the challenges faced by BCI research. This book presents a systemic view of deep learning-based non-invasive BCI systems: starting with the foundations of BCI systems and deep learning algorithms, to the overview of the state-of-the-art deep learning models addressing BCI challenges, detailed typical deep learning algorithms for brain signal analysis, as well as the advanced BCI applications including person authentication, visual reconstruction, language interpretation, assistive living, and neurological disorder diagnosis.

The book also provides a detailed step-by-step tutorial of deep learning-based BCI along with implementable codes and reusable dataset resources. This book is beneficial to a broad range of researchers and students from the fields of computer science, neuroscience, artificial intelligence, and other related interdisciplinary fields.

When asked what attracted him to BCI systems, co-author Xiang Zhang said, “Our initial motivation for working on BCI is to get the power of 'Force' as a Jedi, grasping lightsaber with my mind… Later we found that, more importantly, BCI can bring people a better life, such as improving sleep quality, diagnosing neurological disorders, assisting people who have weak physical abilities, etc. These are the real cool and meaningful things."

His co-author, Lina Yao, who guided Xiang towards research in BCI as his PhD supervisor, agrees, “We believe the Brain-Computer Interface will gradually become an essential part of our everyday lives. The research of BCI is stalwartly driven by multidisciplinary researchers from diverse grounds. In this book, we provide a perspective from the suburb of computer science field, showing how deep learning is capable of reasonably drawing the robust characteristics and meaningful inferences from electroencephalographical (EEG) data, which is acquired from humans' cognitive activities in various contexts.”

Deep Learning for EEG-Based Brain-Computer Interfaces: Representations, Algorithms and Applications retails for US$128 / £115 (hardcover) and is also available in electronic formats. To order or know more about the book, visit


About the Authors

Xiang Zhang is currently a postdoc fellow at Harvard University, USA. He received his PhD degree from the School of Computer Science and Engineering, University of New South Wales, Australia while supervised by Dr Lina Yao. Xiang has a number of publications in notable journals, including Nature Computational Science. Xiang's research interests lie in graph representation learning, data mining, and deep learning with applications in healthcare, Brain-Computer Interfaces, and biomedical sciences.

Lina Yao is currently an Associate Professor at the School of Computer Science and Engineering, University of New South Wales, Australia. Lina is also director of the Data Dynamics Lab (D² Lab) that strives towards developing generalizable machine learning models—as well as designing systems and interfaces—to enable novel ways of human-machine interactions, including an improved understanding of challenges such as robustness, trust, explainability and resilience that improve the human-autonomy partnership. Her research is motivated by, and contributes to, various applications in Information Filtering, Healthcare Informatics, Cyber Security, Transportation, Industry 4.0 and e-commerce.

About World Scientific Publishing Co.

World Scientific Publishing is a leading international independent publisher of books and journals for the scholarly, research and professional communities. World Scientific collaborates with prestigious organisations like the Nobel Foundation and US National Academies Press to bring high quality academic and professional content to researchers and academics worldwide. The company publishes about 600 books and over 140 journals in various fields annually. To find out more about World Scientific, please visit

For more information, contact Amanda at

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.