Targeted optimal treatment regime learning using summary statistics

Learning Summary Statistics for Approximate Bayesian Computation

In high dimensional data, it is often very difficult to analytically evaluate the likelihood function, and thus hard to get a Bayesian posterior estimation. Approximate Bayesian Computation is an important algorithm in this application. However, to apply the algorithm, we need to compress the data into low dimensional summary statistics, which is typically hard to get in an analytical form. In ...

Summary statistics in vision

Incrementally Learning Parameters of Stochastic Context-Free Grammars using Summary Statistics and Repeated Sampling

We are interested in how robots might learn language from exposure to utterances and sensory information about the physical contexts in which they occur. Although stochastic context free grammars are often used to represent the syntactic structure of natural languages, most algorithms for learning them from data require repeated processing of a corpus of sentences. The memory and computational ...

REGIME AWARE LEARNING Regime Aware Learning

We propose a regime aware learning algorithm to learn a sequence of Bayesian networks (BNs) that model a system that undergoes regime changes. The last BN in the sequence represents the system’s current regime, and should be used for BN inference. To explore the feasibility of the algorithm, we create baseline tests against learning a singe BN, and show that our proposed algorithm outperforms t...

optimal irrigation regime of rice under salinity using swap model

abstract rice is most important agricultural crop of guilan province sensibility to salinity and alkalinity of water and soil. in recent years, using of toxicants and fertilizers in farmlands, constructing several dams upstream, entering agricultural, homemade and industrial sewage in to a river, and drought have decreased gradually discharge of river and increased salinity of sefidrud river as...