Testing the distributed representation hypothesis in object recognition in two open datasets.

Neural representation has long been thought to follow the modularity hypothesis, which states that each type of information corresponds to a specific brain area. Though supported by many studies, this hypothesis surfers the pitfall of inefficiency for information encoding. To overcome difficulties the modularity representation hypothesis faced, researchers have proposed that information may be distributed represented in a specific brain area. The distributed representation hypothesis along with the multi-variate pattern approaches have made great success in detecting representation patterns in the previous decade. However, this hypothesis implicitly requires that the pattern should be transformed in a consistent way with respect to all of the represented information in the specific brain area. And the accuracy and validity of this prediction have never been thoroughly tested. Here in the present study, we tested this prediction in two open datasets compiling the object recognition. We validated the distributed representation patterns in the lateral occipital complex/ventral temporal gyrus where all six classifiers were capable of predicting the correct category represented. Furthermore, we correlated the classifiers' decision function values to the bold signals and found that the decision function value of the logistic regression classifier was exclusively correlated with activities of the same brain area in both datasets. These results support the distributed representation hypothesis and suggest that our neural system may be embedded within the algorithm of a specific classifier.