Both embodied and symbolic accounts of conceptual organization would predict partial sharing and partial differentiation between the neural activations seen for concepts activated via different stimulus modalities. But cross-participant and cross-session variability in BOLD activity patterns makes analyses of such patterns with MVPA methods challenging. Here, we examine the effect of cross-modal and individual variation on the machine learning analysis of fMRI data recorded during a word property generation task. We present the same set of living and non-living concepts (land-mammals, or work tools) to a cohort of Japanese participants in two sessions: the first using auditory presentation of spoken words; the second using visual presentation of words written in Japanese characters. Classification accuracies confirmed that these semantic categories could be detected in single trials, with within-session predictive accuracies of 80–90%. However cross-session prediction (learning from auditory-task data to classify data from the written-word-task, or vice versa) suffered from a performance penalty, achieving 65–75% (still individually significant at p « 0.05). We carried out several follow-on analyses to investigate the reason for this shortfall, concluding that distributional differences in neither time nor space alone could account for it. Rather, combined spatio-temporal patterns of activity need to be identified for successful cross-session learning, and this suggests that feature selection strategies could be modified to take advantage of this.

Herein, we propose a new deep neural network model based on invariant information clustering (IIC), proposed by Ji et al., to improve the modeling performance of the leave-one-site-out cross-validation (LOSO-CV) for a multi-source dataset. Our Extended IIC (EIIC) is a type of contrastive learning; however, unlike the original IIC, it is characterized by transfer learning with labeled data pairs, but without the need for a data augmentation technique. Each site in LOSO-CV is left out in turn from the remaining sites used for training and receives a value for modeling evaluation. We applied the EIIC to the resting state functional connectivity magnetic resonance imaging dataset of the Autism Brain Imaging Data Exchange. The challenging nature of brain analysis for autism spectrum disorder (ASD) can be attributed to the variability of subjects, particularly the rapid change in the neural system of children as the target ASD age group. However, EIIC demonstrated higher LOSO-CV classification accuracy for the majority of scanning locations than previously used methods. Particularly, with the adjustment of a mini-batch size, EIIC outperformed other classifiers with an accuracy >0.8 for the sites with highest mean age of the subjects. Considering its effectiveness, our proposed method might be promising for harmonization in other domains, owing to its simplicity and intrinsic flexibility.

Multivariate classification techniques have proven to be powerful tools for distinguishing experimental conditions in single sessions of functional magnetic resonance imaging (fMRI) data. But they are vulnerable to a considerable penalty in classification accuracy when applied across sessions or participants, calling into question the degree to which fine-grained encodings are shared across subjects. Here, we introduce joint learning techniques, where feature selection is carried out using a held-out subset of a target dataset, before training a linear classifier on a source dataset. Single trials of functional MRI data from a covert property generation task are classified with regularized regression techniques to predict the semantic class of stimuli. With our selection techniques (joint ranking feature selection (JRFS) and disjoint feature selection (DJFS)), classification performance during cross-session prediction improved greatly, relative to feature selection on the source session data only. Compared with JRFS, DJFS showed significant improvements for crossparticipant classification. And when using a groupwise training, DJFS approached the accuracies seen for prediction across different sessions from the same participant. Comparing several feature selection strategies, we found that a simple univariate ANOVA selection technique or a minimal searchlight (one voxel in size) is appropriate, compared with larger searchlights.

Some open theoretical questions are addressed on how the mind and brain represent and process concepts, particularly as they are instantiated in particular human languages. Recordings of neuroimaging data should provide a suitable empirical basis for investigating this topic, but the complexity and variety of language demands appropriate data-driven approaches. In this review we argue for a particular suite of methodologies, based on multivariate classification techniques which have proven to be powerful tools for distinguishing neural and cognitive states in fMRI. A combination of larger scale neuroimaging studies are introduced with different monolingual and bilingual populations, and hybrid computational analyses that use encoded implementations of existing theories of conceptual organisation to probe that data. We develop a suite of methodologies that holds the promise of being able to holistically elicit, record and model neural processing during language comprehension and production.

Brand love is a critical concept for building a relationship between brands and consumers because falling in love with a brand can lead to strong brand loyalty. Despite the importance of marketing strategies, however, the underlying neural mechanisms of brand love remain unclear. The present study used an activation likelihood estimation meta-analysis method to investigate the neural correlates of brand love and compared it with those of maternal and romantic love. In total, 47 experiments investigating brand, maternal, and romantic love were examined, and the neural systems involved for the three loves were compared and contrasted. Results revealed that the putamen and insula were commonly activated in the three loves. Moreover, activated brain regions in brand love were detected in the dorsal striatum. Activated regions for maternal love were detected in the cortical area and globus pallidus and were associated with pair bonds, empathy, and altruism. Finally, those for romantic love were detected in the hedonic, strong passionate, and intimate-related regions, such as the nucleus accumbens and ventral tegmental area. Thus, the common regions of brain activation between brand and romantic love were in the dorsal striatum. Meanwhile, no common activated regions were observed between brand and maternal love except for the regions shared among the three love types. Although brand love shared little with the two interpersonal (maternal and romantic) loves and relatively resembled aspects of romantic rather than maternal love, our results demonstrated that brand love may have intrinsically different dispositions from the two interpersonal loves.