🔬 Neuroscience & Brain Research

Development of domain adaptation methods to enable brain decoding across different imaging paradigms. Our work on domain adaptation-enhanced searchlight analysis allows classification of brain states to transfer from visual perception paradigms to mental imagery paradigms.

This research addresses a fundamental challenge in neuroscience: brain decoding models trained on data from one experimental paradigm (e.g., visual perception) often fail to generalize to related but different paradigms (e.g., mental imagery). Domain adaptation provides a principled solution.

Development of DecNefLab, a modular and interpretable simulation framework for decoded neurofeedback research. The framework enables researchers to simulate DecNef experiments, evaluate different decoder designs, and study the impact of various parameters on neurofeedback efficacy before running costly real experiments.

Decoded neurofeedback (DecNef) is a technique that uses real-time brain decoding to provide individuals with feedback about their own neural patterns, enabling targeted modification of brain representations without explicit instructions. It has potential applications in neuroscience research, neurorehabilitation, and mental health treatment.

Investigation of the properties of unconscious visual information processing in the human brain. Research addresses fundamental questions about what visual information can be processed unconsciously and how it influences subsequent conscious perception and behavior.

This work is part of the PhD research of Ning Mei at BCBL, co-supervised with David Soto.

Systematic search and review of computational tools for analyzing the morphological properties of neurons. This review covers methods for quantifying neuronal structure from microscopy images, including branching patterns, soma size, and dendritic arborization.

Application of neural networks to identify phase transitions in physical systems (e.g., the Ising model). Research on the capabilities of different neural architectures for detecting phase transitions from simulated data, with connections to statistical physics and computational neuroscience.

Early work (2010–2015) on applying machine learning to the analysis of MEG and EEG brain signals. Development of classification methods for brain-computer interface (BCI) applications, including the decoding of motor imagery and cognitive states from electrophysiological recordings.

Neuroscience research is conducted in collaboration with:

• Basque Center on Cognition, Brain and Language (BCBL)
• University of the Basque Country (UPV/EHU)
• International partners in computational neuroscience

• Mei N, Santana R and Soto D (2022). Informative neural representations of unseen contents during higher-order processing in human brains and deep artificial networks. Nature Human Behaviour.
• Mei N, Santana R and Soto D (2021). Informative neural representations of unseen objects during higher-order processing in human brains and in deep artificial networks. bioRxiv.
• Mei N, Carreiras M, Santana R and Pylkkänen L (2019). How the brain encodes meaning: Comparing word embedding and computer vision models to predict fMRI data. NeurIPS Workshop.
• Soto D, Sheikh UA, Mei N and Santana R (2020). Decoding and encoding models reveal the role of mental simulation in the brain representation of meaning. Royal Society Open Science.
• Santana R, Mendiburu A and Lozano JA (2019). GP-based methods for domain adaptation: Using brain decoding across subjects as a test-case. GECCO 2019.
• Santana R, Bielza C and Larrañaga P (2012). Regularized logistic regression and multi-objective variable selection for classifying MEG data. Biological Cybernetics.
• Santana R, Yue C and Ocampo-Pineda M (2012). Introducing the use of model-based evolutionary algorithms for EEG-based motor imagery classification. GECCO 2012.
• Santana R, Bielza C and Larrañaga P (2011). An ensemble of classifiers approach with multiple sources of information. ICCST 2011.
• Astigarraga A, Arruti A, Muguerza J, Santana R, Martin JI and Sierra B (2014). User Adapted Motor-Imaginary Brain-Computer Interface by means of EEG Channel Selection based on Estimation of Distributed Algorithms. Scientific World Journal.
• Zheng D, Guo K and Santana R (2015). Comparison of Classification Methods for EEG-based Emotion Recognition. ISNN 2015.
• Santana R et al. (2015). Multi-view classification of psychiatric conditions based on saccades. GECCO 2015.