A Graph-Based Decoding Model for Incomplete Multi-Subject fMRI Functional Alignment

arXiv.org Machine Learning

Aggregating multi-subject fMRI data is indispensable for generating valid and general inferences from patterns distributed across human brains. The disparities in anatomical structures and functional topographies of human brains call for aligning fMRI data across subjects. However, the existing functional alignment methods cannot tackle various kinds of fMRI datasets today, especially when they are incomplete, i.e., some of the subjects probably lack the responses to some stimuli, or different subjects might follow different sequences of stimuli. In this paper, a cross-subject graph that depicts the (dis)similarities between samples across subjects is taken as prior information for developing a more flexible framework that suits an assortment of fMRI datasets. However, the high dimension of fMRI data and the use of multiple subjects makes the crude framework time-consuming or unpractical. Therefore, we regularize the framework so that a feasible kernel-based optimization, which permits non-linear feature extraction, could be theoretically developed. Specifically, a low-dimension assumption is imposed on each new feature space to avoid overfitting caused by the high-spatial-low-temporal resolution of fMRI data. Empirical studies confirm that the proposed method under both incompleteness and completeness can achieve better performance than other state-of-the-art functional alignment methods under completeness.

Management AI types with machine learning MarkTechPost


Through the assistance of machine learning, it's possible to create and manage a variety of systems. For the future of development, however, it's important that everyone can have a base knowledge of the management systems that make up artificial intelligence. In this referred article from Forbes, we will discuss some of the main management systems for most modern AI. As part of any machine learning, an artificial neural network is one of the most commonly discussed items regarding AI. This concept dates all the way back to the year 1943 in which two individuals developed a brain model for logic and mathematics.

Stop Using Introspection to Gather Data for the Design of Computational Modeling and Spatial Assistance

AAAI Conferences

Research in spatial cognition offers a wide spectrum of possibilities to combine psychological and computational approaches. Sometimes, the design of computational systems may merely be based on what researchers believe happen in their minds when solving spatial reasoning problems. In other cases, an already existing computational approach is enabled post hoc as cognitively adequate, or psychologically valid. In the contribution, it will be argued that carefully conducted experiments with human participants are needed to understand spatial cognition. Based on such experiments, the contribution will then clarify the role of visual images and spatial representations in human reasoning and problem-solving. What is represented in such representations?


AAAI Conferences

Some systems are strange, near-bugs that turn out upon deeper analysis to be absolutely fundamental. This paper develops the notion of strangeness with respect to one class of AI system, cognitive architectures. It describes the detection of strange new architectures and their synthesis with conventional architectures.

Multi-Region Neural Representation: A novel model for decoding visual stimuli in human brains

arXiv.org Machine Learning

Multivariate Pattern (MVP) classification holds enormous potential for decoding visual stimuli in the human brain by employing task-based fMRI data sets. There is a wide range of challenges in the MVP techniques, i.e. decreasing noise and sparsity, defining effective regions of interest (ROIs), visualizing results, and the cost of brain studies. In overcoming these challenges, this paper proposes a novel model of neural representation, which can automatically detect the active regions for each visual stimulus and then utilize these anatomical regions for visualizing and analyzing the functional activities. Therefore, this model provides an opportunity for neuroscientists to ask this question: what is the effect of a stimulus on each of the detected regions instead of just study the fluctuation of voxels in the manually selected ROIs. Moreover, our method introduces analyzing snapshots of brain image for decreasing sparsity rather than using the whole of fMRI time series. Further, a new Gaussian smoothing method is proposed for removing noise of voxels in the level of ROIs. The proposed method enables us to combine different fMRI data sets for reducing the cost of brain studies. Experimental studies on 4 visual categories (words, consonants, objects and nonsense photos) confirm that the proposed method achieves superior performance to state-of-the-art methods.