Neuroscience and Network Dynamics Toward Brain-Inspired Intelligence

Recall Network: A Simple Brain-Inspired Algorithm for Classification

The latest development of neuroscience has deepened the understanding of the information-processing mechanisms in the human brain and inspired a couple of sophisticated computational methods, such as deep learning, memory networks, and hierarchical temporal memory. However, it remains a challenge to explore simpler models due to the high computational cost of the above-mentioned methods. This paper proposes recall network (RN), an intuitive and simple model, that initializes itself by constructing the network path derived from the correlation of features in the training dataset and then makes classification decisions by recalling the paths that are relevant to the features in the test set. The algorithm has been applied to 263 datasets available from UCI Machine Learning Repository, and the classification results of repeated 10-fold cross-validation experiments on Weka demonstrate its competitive performance with prestigious classification algorithms, such as ANN, J48, and KNN.

Functional Brain Network Analysis of Knowledge Transfer While Engineering Problem-Solving

As a complex cognitive activity, knowledge transfer is mostly correlated to cognitive processes such as working memory, behavior control, and decision-making in the human brain while engineering problem-solving. It is crucial to explain how the alteration of the functional brain network occurs and how to express it, which causes the alteration of the cognitive structure of knowledge transfer. However, the neurophysiological mechanisms of knowledge transfer are rarely considered in existing studies. Thus, this study proposed functional connectivity (FC) to describe and evaluate the dynamic brain network of knowledge transfer while engineering problem-solving. In this study, we adopted the modified Wisconsin Card-Sorting Test (M-WCST) reported in the literature. The neural activation of the prefrontal cortex was continuously recorded for 31 participants using functional near-infrared spectroscopy (fNIRS). Concretely, we discussed the prior cognitive level, knowledge transfer distance, and transfer performance impacting the wavelet amplitude and wavelet phase coherence. The paired t-test results showed that the prior cognitive level and transfer distance significantly impact FC. The Pearson correlation coefficient showed that both wavelet amplitude and phase coherence are significantly correlated to the cognitive function of the prefrontal cortex. Therefore, brain FC is an available method to evaluate cognitive structure alteration in knowledge transfer. We also discussed why the dorsolateral prefrontal cortex (DLPFC) and occipital face area (OFA) distinguish themselves from the other brain areas in the M-WCST experiment. As an exploratory study in NeuroManagement, these findings may provide neurophysiological evidence about the functional brain network of knowledge transfer while engineering problem-solving.