Classifier design given an uncertainty class of feature distributions via regularized maximum likelihood and the incorporation of biological pathway knowledge in steady-state phenotype classification.
Mohammad Shahrokh EsfahaniJason M. KnightAmin ZollanvariByung-Jun YoonEdward R. DoughertyPublished in: Pattern Recognit. (2013)
Keyphrases
- steady state
- class labels
- maximum likelihood
- support vector machine
- markov chain
- classification accuracy
- feature distributions
- feature selection
- feature set
- queue length
- feature space
- steady states
- queueing networks
- training set
- training data
- feature extraction
- product form
- learning algorithm
- explicit expressions
- machine learning
- multi class
- feature vectors
- reinforcement learning
- arrival rate
- queueing model
- variance estimator