Bayesian Network Classifiers

By Nir Friedman, Dan Geiger, Moisés Goldszmidt. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Evaluation of machine learning classifiers for mobile malware detection (2014, unknown): “Necessary probabilities can calculate directly from training data by substituting the foregoing decision value in the loop (Friedman et al. 1997).”
Bayesian Networks In Educational Testing (2002, background): “This means that in order to maximize CLL for a fixed model structure we would have to search over the whole space of model parameters[9].”
Deep learning and machine vision for food processing: A survey (2021, background): “…let 𝐺 = (𝐼, 𝐸) represent a directed acyclic graph (where 𝐼 is the set of all nodes in the graph and 𝐸 is the set of directed connected line segments) and let 𝑋 = (𝑋 & ), 𝑖 ∈ 𝐼 be the random variable that is represented by a node 𝑖 in the directed acyclic graph (Friedman et al., 1997).”
Prediction of Slope Stability using Naive Bayes Classifier (2018, methodology): “When x1, x2, …, xn are discrete, using the Bayes’ theorem, the conditional probability of the kth possible outcome can be expressed as follows (Domingos and Pazzani, 1997; Friedman et al., 1997; Shirzadi et al., 2017).”
Testing the significance of attribute interactions (2004, background): “Based on this quantification it is possible to analyze relationships between attributes, perform attribute clustering and guide feature selection and construction (Jakulin & Bratko, 2003).”
Big data for cyber physical systems in industry 4.0: a survey (2019, methodology): “To solve this dependency issue, Bayesian network is proposed to improve prediction performance (Friedman, Geiger, and Goldszmidt 1997).”
Comparison of machine learning and traditional classifiers in glaucoma diagnosis (2002, background): “Naive Bayes' classifier [5] assumes independency between components of input .”
Spoken language understanding using the Hidden Vector State Model (2006, methodology): “The dialog act decoder uses the Bayesian Network approach proposed in (Meng et al., 2000) extended to use Tree-Augmented Naive Bayes (TAN) networks (Friedman et al., 1997) in order to model between-concept dependencies.”
Comprehensible classification models: a position paper (2014, methodology): “More sophisticated types of Bayesian Network Classifiers (BNCs) do not have the Naïve Bayes’ strong assumption of attribute independence; they allow the modeling of attribute dependencies, represented by edges between attributes (nodes) in a network [27], [11].”
Bayesian Networks and Influence Diagrams: A Guide to Construction and Analysis (2007, methodology): “For instance, the tree-augmented naive Bayes model (Friedman et al. 1997) appears as a natural extension of the naive Bayes model, while the hierarchical naive Bayes model (Zhang 2004) is another extension of the naive Bayes model.”