No abstract

In the age of artificial intelligence, the best approach to handling huge amounts of data is a tremendously motivating and hard problem. Among machine learning models, stochastic gradient descent (SGD) is not only simple but also very effective. This study provides a detailed analysis of contemporary state-of-the-art deep learning applications, such as natural language processing (NLP), visual data processing, and voice and audio processing. Following that, this study introduces several versions of SGD and its variant, which are already in the PyTorch optimizer, including SGD, Adagrad, adadelta, RMSprop, Adam, AdamW, and so on. Finally, we propose theoretical conditions under which these methods are applicable and discover that there is still a gap between theoretical conditions under which the algorithms converge and practical applications, and how to bridge this gap is a question for the future.

Lyme borreliosis, recognized as one of the most important tick-borne diseases worldwide, has been increasing in incidence and spatial extent. Currently, there are few geographic studies about the distribution of Lyme borreliosis risk across China. Here we established a nationwide database that involved Borrelia burgdorferi sensu lato ( B. burgdorferi ) detected in humans, vectors, and animals in China. The eco-environmental factors that shaped the spatial pattern of B. burgdorferi were identified by using a two-stage boosted regression tree model and the model-predicted risks were mapped. During 1986−2020, a total of 2,584 human confirmed cases were reported in 25 provinces. Borrelia burgdorferi was detected from 35 tick species with the highest positive rates in Ixodes granulatus , Hyalomma asiaticum , Ixodes persulcatus , and Haemaphysalis concinna ranging 20.1%−24.0%. Thirteen factors including woodland, NDVI, rainfed cropland, and livestock density were determined as important drivers for the probability of B. burgdorfer i occurrence based on the stage 1 model. The stage 2 model identified ten factors including temperature seasonality, NDVI, and grasslands that were the main determinants used to distinguish areas at high or low-medium risk of B. burgdorferi , interpreted as potential occurrence areas within the area projected by the stage 1 model. The projected high-risk areas were not only concentrated in high latitude areas, but also were distributed in middle and low latitude areas. These high-resolution evidence-based risk maps of B. burgdorferi was first created in China and can help as a guide to future surveillance and control and help inform disease burden and infection risk estimates.