When humans learn a new concept, they might ignore examples that they cannot make sense of at first, and only later focus on such examples, when they are more useful for learning. We propose incorporating this idea of tunable sensitivity for hard examples in neural network learning, using a new generalization of the cross-entropy gradient step, which can be used in place of the gradient in any ...

Three hundred eighty-seven undergraduate students in a large-group setting were exposed to 20 min of either meditation, progressive muscle relaxation (PMR), or a control condition, followed by 1 min of stress induction and another 10 min of each intervention. Participants in the meditation and PMR groups decreased more in cognitive, somatic, and general state anxiety than controls. The PMR grou...

BACKGROUND People who inject drugs (PWID) often encounter barriers when attempting to access health care and social services. In our previous study conducted to identify barriers to accessing care from the perspective of PWIDs in Saskatoon, Canada: poverty, lack of personal support, discrimination, and poor knowledge and coordination of service providers among other key barriers were identified...

In the absence of a national newborn hearing screening program in Italy, parent associations have been working with the Italian Paediatric Federation (FIMP), the Society of Neonatology (SIN) and members of the Italian Society of Audiology and Phoniatrics (SIAF) to promote guidelines, best practice and training courses in early hearing detection intervention that incorporate sensitivity training...

Transformer models are widely used in AI applications such as Natural Language Processing (NLP), Computer Vision (CV), etc. However, enormous computation workload be-comes an obstacle to train large transformer efficiently. Recently, some methods focus on reducing the during training by skipping layers. How-ever, these use simple probability distribution and coarse-grained calculation, which si...

Uncertainty estimation is an essential step in the evaluation of robustness for deep learning models computer vision, especially when applied risk-sensitive areas. However, most state-of-the-art either fail to obtain uncertainty or need significant modification (e.g., formulating a proper Bayesian treatment) it. Most previous methods are not able take arbitrary model off shelf and generate with...