The aim of this work is to develop a practical framework, which extends the classical Hidden Markov Models (HMM) for continuous speech recognition based on the Maximum Entropy (MaxEnt) principle. The MaxEnt models can estimate the posterior probabilities directly as with Hybrid NN/HMM connectionist speech recognition systems. In particular, a new acoustic modelling based on discriminative MaxEn...

Probabilistic reasoning under the so-called principle of maximum entropy is a viable and convenient alternative to Bayesian networks, relieving the user from providing complete (local) probabilistic information and observing rigorous conditional independence assumptions. In this paper, we present a novel approach to performing computational MaxEnt reasoning that makes use of symbolic computatio...

The analysis of discrimination, feature and model selection conduct to the discussion of the relationships between Support Vector Machine (SVM), Bayesian and Maximum Entropy (MaxEnt) formalisms. MaxEnt discrimination can be seen as a particular case of Bayesian inference, which at its turn can be seen as a regularization approach applicable to SVM. Probability measures can be attached to each f...

The aim of this work is to develop a practical framework, which extends the classical Hidden Markov Models (HMM) for continuous speech recognition based on the Maximum Entropy (MaxEnt) principle. The MaxEnt models can estimate the posterior probabilities directly as with Hybrid NN/HMM connectionist speech recognition systems. In particular, a new acoustic modelling based on discriminative MaxEn...

Maximum entropy (Maxent) modeling has great potential for identifying distributions and habitat selection of wildlife given its reliance on only presence locations. Recent studies indicate Maxent is relatively insensitive to spatial errors associated with location data, requires few locations to construct useful models, and performs better than other presence-only modeling approaches. Further a...

In the present study, we have defined, so-called, MaxEnt and MinxEnt functionals on the set of corresponding moment vector functions via the MaxEnt and MinxEnt optimization measures. By virtue of these functionals we have obtained two new distributions – MinMaxEnt and MaxMinxEnt distributions. The approach to obtain mentioned distributions can be formulated as a generalization of MaxEnt and Min...

Maximum Entropy (maxent) models are an attractive formalism for statistical models of many types and have been used for a number of purposes, including language modeling (Rosenfeld 1994), part of speech tagging (Ratnaparkhi 1996), prepositional phrase attachment (Ratnaparkhi 1998), sentence breaking (Reynar and Ratnaparkhi 1997) and parsing (Ratnaparkhi 1997). Maxent models allow the combinatio...

We propose a natural generalization of Regularized Maximum Entropy Density Estimation (maxent) to handle input data with unknown values. While standard approaches to handling missing data usually involve estimating the actual unknown values, then using the estimated, complete data as input, our method avoids the two-step process and handles unknown values directly in the maximum entropy formula...

BACKGROUND Rare or narrowly endemic organisms are difficult to monitor and conserve when their total distribution and habitat preferences are incompletely known. One method employed in determining distributions of these organisms is species distribution modeling (SDM). METHODS Using two species of narrowly endemic burrowing crayfish species as our study organisms, we sought to ground validate...

In density estimation task, maximum entropy model (Maxent) can effectively use reliable prior information via certain constraints, i.e., linear constraints without empirical parameters. However, reliable prior information is often insufficient, and the selection of uncertain constraints becomes necessary but poses considerable implementation complexity. Improper setting of uncertain constraints...