Multimodal behavior involves multiple processing stations distributed across distant brain regions, but our understanding of how such distributed processing is coordinated in the brain is limited. Here we take a decoding approach to this problem, aiming to quantify how temporal aspects of brain-wide neural activity may be used to infer specific multimodal behaviors. Using high temporal resolution measurements by MEG, we detect bursts of activity from hundreds of locations across the surface of the brain at millisecond resolution. We then compare decoding using three characteristics of neural activity bursts, decoding with event counts, with latencies and with time differences between pairs of events. Training decoders in this regime is particularly challenging because the number of samples is smaller by orders of magnitude than the input dimensionality. We develop a new decoding approach for this regime that combines non-parametric modelling with aggressive feature selection. Surprisingly, we find that decoding using time-differences, based on thousands of region pairs, is significantly more accurate than using other activity characteristics, reaching 90% accuracy consistently across subjects. These results suggest that relevant information about multimodal brain function is provided by subtle time differences across remote brain areas.
Bruno Kessler Foundation（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）
Brain decoding is a data analysis paradigm for neuroimaging experiments that is based on predicting the stimulus presented to the subject from the concurrent brain activity. In order to make inference at the group level, a straightforward but sometimes unsuccessful approach is to train a classifier on the trials of a group of subjects and then to test it on unseen trials from new subjects. The extreme difficulty is related to the structural and functional variability across the subjects. We call this approach "decoding across subjects". In this work, we address the problem of decoding across s…
Multivariate pattern analysis (MVPA) or brain decoding methods have become standard practice in analysing fMRI data. Although decoding methods have been extensively applied in Brain Computing Interfaces (BCI), these methods have only recently been applied to time-series neuroimaging data such as MEG and EEG to address experimental questions in Cognitive Neuroscience. In a tutorial-style review, we describe a broad set of options to inform future time-series decoding studies from a Cognitive Neuroscience perspective. Using example MEG data, we illustrate the effects that different options in th…
Department of Neuroscience and Biomedical Engineering, Aalto University School of Science（阿尔托大学理学院神经科学与生物医学工程系）；Aalto NeuroImaging, Aalto University（阿尔托大学阿尔托神经成像中心）；Aalto University School of Science（阿尔托大学理学院）；Aalto University（阿尔托大学）
Convolutional Neural Networks (CNN) outperform traditional classification methods in many domains. Recently these methods have gained attention in neuroscience and particularly in brain-computer interface (BCI) community. Here, we introduce a CNN optimized for classification of brain states from magnetoencephalographic (MEG) measurements. Our CNN design is based on a generative model of the electromagnetic (EEG and MEG) brain signals and is readily interpretable in neurophysiological terms. We show here that the proposed network is able to decode event-related responses as well as modulations …
We propose a fusion approach that combines features from simultaneously recorded electroencephalographic (EEG) and magnetoencephalographic (MEG) signals to improve classification performances in motor imagery-based brain-computer interfaces (BCIs). We applied our approach to a group of 15 healthy subjects and found a significant classification performance enhancement as compared to standard single-modality approaches in the alpha and beta bands. Taken together, our findings demonstrate the advantage of considering multimodal approaches as complementary tools for improving the impact of non-inv…
In this study we present a kernel based convolution model to characterize neural responses to natural sounds by decoding their time-varying acoustic features. The model allows to decode natural sounds from high-dimensional neural recordings, such as magnetoencephalography (MEG), that track timing and location of human cortical signalling noninvasively across multiple channels. We used the MEG responses recorded from subjects listening to acoustically different environmental sounds. By decoding the stimulus frequencies from the responses, our model was able to accurately distinguish between two…
The human brain is constantly processing and integrating information in order to make decisions and interact with the world, for tasks from recognizing a familiar face to playing a game of tennis. These complex cognitive processes require communication between large populations of neurons. The non-invasive neuroimaging methods of electroencephalography (EEG) and magnetoencephalography (MEG) provide population measures of neural activity with millisecond precision that allow us to study the temporal dynamics of cognitive processes. However, multi-sensor M/EEG data is inherently high dimensional…
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）；School of Electrical and Information Engineering, Zhengzhou University（郑州大学电气工程学院）
Neuroimaging techniques have shown to be useful when studying the brain's activity. This paper uses Magnetoencephalography (MEG) data, provided by the Human Connectome Project (HCP), in combination with various deep artificial neural network models to perform brain decoding. More specifically, here we investigate to which extent can we infer the task performed by a subject based on its MEG data. Three models based on compact convolution, combined convolutional and long short-term architecture as well as a model based on multi-view learning that aims at fusing the outputs of the two stream netw…
Université de Montréal（蒙特利尔大学）；Mila – Quebec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）；IMT Atlantique（IMT大西洋国立高等矿业电信学校）；IVADO, Université de Montréal（蒙特利尔大学IVADO研究所）；Hôpital du Sacré-Cœur de Montréal, Santé Québec Nord-de-l’Île-de-Montréal - Universitaire（蒙特利尔圣心医院，魁北克健康部蒙特利尔岛北-大学网络）；Faculty of Medicine, Université de Montréal（蒙特利尔大学医学院）
University of Catania（卡塔尼亚大学）；University of Central Florida（中佛罗里达大学）
This work presents a novel method of exploring human brain-visual representations, with a view towards replicating these processes in machines. The core idea is to learn plausible computational and biological representations by correlating human neural activity and natural images. Thus, we first propose a model, EEG-ChannelNet, to learn a brain manifold for EEG classification. After verifying that visual information can be extracted from EEG data, we introduce a multimodal approach that uses deep image and EEG encoders, trained in a siamese configuration, for learning a joint manifold that max…
A Pre-trained Framework for Multilingual Brain Decoding Using Non-invasive Recordings
Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Hong Kong Baptist University（香港 Baptist大学）
