We show how to adjust for the variance introduced by dropout with corrections to weight initialization and Batch Normalization, yielding higher accuracy. Though dropout can preserve the expected input to a neuron between train and test, the variance of the input differs. We thus propose a new weight initialization by correcting for the influence of dropout rates and an arbitrary nonlinearity’s ...

OBJECTIVE The aim of this study was to use pretreatment and treatment factors to predict dropout from residential substance use disorder program and to examine how the treatment environment modifies the risk for dropout. METHOD This study assessed 3649 male patients at entry to residential substance use disorder treatment and obtained information about their perceptions of the treatment envir...

Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways. Due to its popularity in deep learning, dropout has been applied also for this class of problems. Despite its solid empirical performance, the theoretical properties of dropout as a regularizer remain quite elusive for this class of problems. In this paper, we present a theoretic...

Distance Education courses are present in large number of educational institutions. Virtual Learning Environments development contributes to this wide adoption of Distance Education modality and allows new pedagogical methodologies. However, dropout rates observed in these courses are very expressive, both in public and private educational institutions. This paper presents a Learning Analytics ...

Studies of student risk of school dropout have shown that current predictors of “at-risk” status do not accurately identify a large percentage of students who eventually dropout. Through the analysis of the entire grade 1-12 longitudinal cohort-based grading histories of the class of 2006 for two school districts in the United States, this study extends past longitudinal conceptions of dropout ...

abstract Deep learning is the state-of-the-art in fields such as visual object recognition and speech recognition. This learning uses a large number of layers and a huge number of units and connections. Therefore, overfitting is a serious problem with it, and the dropout which is a kind of regularization tool is used. However, in online learning, the effect of dropout is not well known. This pa...

Dropout prediction in MOOCs is a well-researched problem where we classify which students are likely to persist or drop out of a course. Most research into creating models which can predict outcomes is based on student engagement data. Why these students might be dropping out has only been studied through retroactive exit surveys. This helps identify an important extension area to dropout predi...

Dropout and other feature noising schemes control overfitting by artificially corrupting the training data. For generalized linear models, dropout performs a form of adaptive regularization. Using this viewpoint, we show that the dropout regularizer is first-order equivalent to an L2 regularizer applied after scaling the features by an estimate of the inverse diagonal Fisher information matrix....

The main goal was to test if teacher-student relationships and achievement motivation are predicting dropout intention equally for low and high socio-economic status students. A questionnaire measuring teacher-student relationships and achievement motivation was administered to 2,360 French Canadian secondary students between 12 and 15 years old during the spring of 2005. A hierarchical multipl...

Dropout is a popular stochastic regularization technique for deep neural networks that works by randomly dropping (i.e. zeroing) units from the network during training. This randomization process allows to implicitly train an ensemble of exponentially many networks sharing the same parametrization, which should be averaged at test time to deliver the final prediction. A typical workaround for t...