#### Filter Results:

- Full text PDF available (63)

#### Publication Year

1999

2017

- This year (13)
- Last 5 years (67)
- Last 10 years (94)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Brain Region

#### Cell Type

#### Data Set Used

#### Key Phrases

#### Method

#### Organism

Learn More

- José M. Peña, Roland Nilsson, Johan Björkegren, Jesper Tegnér
- Int. J. Approx. Reasoning
- 2007

We propose algorithms for learning Markov boundaries from data without having to learn a Bayesian network first. We study their correctness, scalability and data efficiency. The last two properties are important because we aim to apply the algorithms to identify the minimal set of features that is needed for probabilistic classification in databases with… (More)

- José M. Peña, José Antonio Lozano, Pedro Larrañaga
- Pattern Recognition Letters
- 1999

- Roland Nilsson, José M. Peña, Johan Björkegren, Jesper Tegnér
- Journal of Machine Learning Research
- 2007

We analyze two different feature selection problems: finding a minimal feature set optimal for classification (MINIMAL-OPTIMAL) vs. finding all features relevant to the target variable (ALLRELEVANT). The latter problem is motivated by recent applications within bioinformatics, particularly gene expression analysis. For both problems, we identify classes of… (More)

- Shama Desai Ahuja, David Ashkin, +69 authors Jae Joon Yim
- PLoS medicine
- 2012

BACKGROUND
Treatment of multidrug resistant tuberculosis (MDR-TB) is lengthy, toxic, expensive, and has generally poor outcomes. We undertook an individual patient data meta-analysis to assess the impact on outcomes of the type, number, and duration of drugs used to treat MDR-TB.
METHODS AND FINDINGS
Three recent systematic reviews were used to identify… (More)

- Jens Dalgaard Nielsen, Tomas Kocka, José M. Peña
- UAI
- 2003

This paper proposes and evaluates the k-greedy equivalence search algorithm (KES) for learning Bayesian networks (BNs) from complete data. The main characteristic of KES is that it allows a trade-off between greediness and randomness, thus exploring different good local optima when run repeatedly. When greediness is set at maximum, KES corresponds to the… (More)

- José M. Peña, Johan Björkegren, Jesper Tegnér
- ECSQARU
- 2005

We propose an algorithm for learning the Markov boundary of a random variable from data without having to learn a complete Bayesian network. The algorithm is correct under the faithfulness assumption, scalable and data efficient. The last two properties are important because we aim to apply the algorithm to identify the minimal set of random variables that… (More)

- Inmaculada Tasset, René Drucker-Colín, +4 authors Isaac Túnez
- Neurochemical Research
- 2010

We studied the effects of transcranial magnetic stimulation (TMS, 60 Hz and 0.7 mT for 4 h/day for 14 days) on oxidative and cell damage caused by olfactory bulbectomy (OBX) in Wistar rats. The levels of lipid peroxidation products and caspase-3 were enhanced by OBX, whereas it prompted a reduction in reduced glutathione (GSH) content and antioxidative… (More)

This paper shows how the Bayesian network paradigm can be used in order to solve com binatorial optimization problems. To do it some methods of structure learning from data and simulation of Bayesian networks are in serted inside Estimation of Distribution Al gorithms (EDA). EDA are a new tool for evo lutionary computation in which populations of… (More)

- José M. Peña
- EvoBIO
- 2008

In many cases what matters is not whether a false discovery is made or not but the expected proportion of false discoveries among all the discoveries made, i.e. the so-called false discovery rate (FDR). We present an algorithm aiming at controlling the FDR of edges when learning Gaussian graphical models (GGMs). The algorithm is particularly suitable when… (More)

- José M. Peña
- AISTATS
- 2007

We apply MCMC to approximately calculate (i) the ratio of directed acyclic graph (DAG) models to DAGs for up to 20 nodes, and (ii) the fraction of chain graph (CG) models that are neither undirected graph (UG) models nor DAG models for up to 13 nodes. Our results suggest that, for the numbers of nodes considered, (i) the ratio of DAG models to DAGs is not… (More)