Distinct roles of excitatory and inhibitory neurons in the medial prefrontal cortex in the expression and reconsolidation of methamphetamine-associated memory in male mice.

Methamphetamine, a commonly abused drug, is known for its high relapse rate. The persistence of addictive memories associated with methamphetamine poses a significant challenge in preventing relapse. Memory retrieval and subsequent reconsolidation provide an opportunity to disrupt addictive memories. However, the key node in the brain network involved in methamphetamine-associated memory retrieval has not been clearly defined. In this study, using the conditioned place preference in male mice, whole brain c-FOS mapping and functional connectivity analysis, together with chemogenetic manipulations of neural circuits, we identified the medial prefrontal cortex (mPFC) as a critical hub that integrates inputs from the retrosplenial cortex and the ventral tegmental area to support both the expression and reconsolidation of methamphetamine-associated memory during its retrieval. Surprisingly, with further cell-type specific analysis and manipulation, we also observed that methamphetamine-associated memory retrieval activated inhibitory neurons in the mPFC to facilitate memory reconsolidation, while suppressing excitatory neurons to aid memory expression. These findings provide novel insights into the neural circuits and cellular mechanisms involved in the retrieval process of addictive memories. They suggest that targeting the balance between excitation and inhibition in the mPFC during memory retrieval could be a promising treatment strategy to prevent relapse in methamphetamine addiction.

Few-Shot Rolling Bearing Fault Diagnosis with Metric-Based Meta Learning.

Fault diagnosis methods based on deep learning and big data have achieved good results on rotating machinery. However, the conventional deep learning method of bearing fault diagnosis is mostly based on laboratory artificial simulation data, and there is an error with actual fault data, which will reduce the generalization performance of the deep learning method. In addition, labeled data are very precious in real industrial environment. Due to expensive equipment and personnel safety issues, it is difficult to obtain a large amount of high-quality fault labeling data. Therefore, in this paper, we propose a metric-based meta-learning method named Reinforce Relation Network (RRN) for diagnosing bearing faults with few-shot samples. In the proposed method, a 1D convolution neural network is used to extract fault features, and a metric learner is used to predict the similarity between samples under different transfer conditions. Label smoothing and the Adabound algorithm are utilized to further improve the performance of network classification. The performance of the proposed method is verified on a dataset which contains artificial damage and natural damage data. The comparison studies with other methods demonstrate the superiority of the proposed method in the few-shot scenario.