We investigate parameter priors for discrete DAG models. It was shown in previous works that a Dirichlet prior on the parameters of a discrete DAG model is inevitable assuming global and local parameter independence for all possible complete DAG structures. A similar result for Gaussian DAG models hinted that the assumption of local independence may be redundant. Herein, we prove that the local...

Strength independence refers to the assumption that in a retrieval-induced forgetting paradigm, the increase in performance for the practiced items (RP+) is independent of the decrease for the related and supposedly inhibited items (RP-). One way in which this assumption has been tested is by examining the correlation over subjects between these two measures. The finding that there is no such c...

Generally, the disorders in a neural network diagnosis model are assumed independent each other. In this paper, we propose a neural network model for diagnostic problem solving where the disorder independence assumption is no longer necessary. Firstly, we characterize the diagnostic tasks and the causal network which is used to represent the diagnostic problem, then we describe the neural netwo...

Large-scale assessments of reading comprehension, notably OECD’s Programme for International Student Achievement (PISA) and IEA’s Progress in Reading Literacy Study (PIRLS), generally use paper-and-pencil tests in which a reading passage, with different questions based on it, is presented to the student. The PISA mathematics and science literacy tests also consist of a hierarchically embedded s...

This paper deals with the use of Bayesian Belief Networks in order to improve the accuracy and training time of character segmentation for unconstrained handwritten text. Comparative experimental results have been evaluated against Naive Bayes classification, which is based on the assumption of the independence of the parameters and two additional previous commonly used methods. Results have de...

Abstract In this paper the goal is to explain predictions from complex machine learning models. One method that has become very popular during last few years Shapley values. The original development of values for prediction explanation relied on assumption features being described were independent. If in reality are dependent may lead incorrect explanations. Hence, there have recently been atte...

The naive Bayes classiier, currently experiencing a renaissance in machine learning, has long been a core technique in information retrieval. We review some of the variations of naive Bayes models used for text retrieval and classiication, focusing on the distributional assumptions made about word occurrences in documents.