Reviews: Learning Neural Representations of Human Cognition across Many fMRI Studies

This paper proposes a new model architecture dedicated to multi-dataset brain decoding classification. Multi-dataset classification is a tricky problem in machine learning, especially when the number of samples is particularly small. In order to solve this problem, the author(s) employed the ideas of knowledge aggregation and transfer learning. The main idea of this paper is interesting but my main concerts are on the limited novelty compared to the previous work. Furthermore, I do not find any references or discussions in order to present the limitation of the proposed methods. Some reconstructive comments are listed as follows: 1.