Global Sensitivity Analysis for MAP Inference in Graphical Models
Authors: Jasper De Bock, Cassio P de Campos, Alessandro Antonucci
NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments with real data sets are reported in Section 5. We consider the problem of recognizing facial action units from real image data using the CK+ data set [10, 16]. Using the MRF, we predict the AU configuration using a MAP algorithm...obtaining about 89% accuracy. In this second experiment, we turn our attention to the classification problem using data sets from the UCI machine learning repository [1]. |
| Researcher Affiliation | Academia | Jasper De Bock Ghent University, SYSTe MS Ghent (Belgium) jasper.debock@ugent.be Cassio P. de Campos Queen s University Belfast (UK) c.decampos@qub.ac.uk Alessandro Antonucci IDSIA Lugano (Switzerland) alessandro@idsia.ch |
| Pseudocode | No | The paper describes algorithmic steps verbally, but it does not contain a formally structured pseudocode block or an explicitly labeled algorithm section. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing its source code or a direct link to a code repository for the described methodology. |
| Open Datasets | Yes | We consider the problem of recognizing facial action units from real image data using the CK+ data set [10, 16]. In this second experiment, we turn our attention to the classification problem using data sets from the UCI machine learning repository [1]. |
| Dataset Splits | No | The paper states 'One third of the posed faces are selected for testing, and two thirds for training the model.' and 'Our empirical results are obtained out of 10 runs of 5-fold cross-validation', which describe train/test splits, but no explicit separate validation split is mentioned. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU or CPU models, memory, or other detailed computer specifications used for running its experiments. |
| Software Dependencies | No | The paper mentions methods like 'linear support vector machine (SVM)', 'MRF', and 'Naive Bayes classifier' but does not specify any software dependencies with version numbers (e.g., Python version, specific library versions). |
| Experiment Setup | Yes | In all tests we have employed a Naive Bayes classifier with equivalent sample size equal to one. |