Deep neural network representation and Generative Adversarial Learning

Application of neural network and nomogram for the prediction of risk factors for bone mineral density abnormalities: A cross-sectional NHANES-based survey

“…In addition to traditional risk factors such as older age, estrogen, vitamin D, and hormone use, among others [ 6 ], dietary structure and electrolyte disorders may also be important risk factors for the onset of an abnormal primary bone mineral density, especially based on the dietary structure of the American population [ 7 ]. Moreover, several algorithm models [ 8 ] have been widely used in the prevention and treatment of bone mineral density abnormalities, for example, Neural network analysis [ 9 , 10 ] can reveal important risk factors related to bone mineral density abnormalities. It simulates the neural network system of the human brain for structural operation, and information processing is achieved by adjusting the network of several internal nodes.But the widely used algorithm currently includes alcohol drinking, age, smoking, parents’ fracture history, height difference (≥4 cm), use of glucocorticoids and other drugs, endocrine diseases, milk, premature menopause history, gender, fracture history, body mass index (BMI), and other conventional risk factors in the study [ 11 ].…”

Optimization of Decision Trees with Hypotheses for Knowledge Representation

“…Note that, to improve the understandability, we should not only try to minimize the number of nodes in a decision tree but also its depth that is the unimprovable upper bound on the number of conditions describing objects accepted by a path from the root to a terminal node of the tree. In this paper, we concentrate only on the consideration of complexity of decision trees and do not study many recent problems considered in machine learning [14][15][16][17].…”

An Information-Theoretic Perspective on Proper Quaternion Variational Autoencoders

“…Generative learning models have been recently gained considerable attention due to their surprising performance in producing highly realistic signals of various types [ 1 , 2 , 3 , 4 ]. They have been successfully employed in a wide variety of applications, such as image-to-image translation [ 5 ], image fusion [ 6 ], face de-identification [ 7 ], natural language generation [ 8 ], data augmentation on ancient handwritten characters [ 9 ], MRI super-resolution [ 10 ], brain tumor growth prediction [ 11 ], generative modeling of structured-data [ 12 ].…”