This paper describes a technique for learning both the number of states and the topology of Hidden Markov Models from examples. The induction process starts with the most specific model consistent with the training data and generalizes by successively merging states. Both the choice of states to merge and the stopping criterion are guided by the Bayesian posterior probability. We compare our algorithm with the Baum-Welch method of estimating fixed-size models, and find that it can induce minimal HMMs from data in cases where fixed estimation does not converge or requires redundant parameters to converge. 1 INTRODUCTION AND OVERVIEW Hidden Markov Models (HMMs) are a well-studied approach to the modelling of sequence data. HMMs can be viewed as a stochastic generalization of finite-state automata, where both the transitions between states and the generation of output symbols are governed by probability distributions. HMMs have been important in speech recognition (Rabiner & Juang, 1986), cryptography, and more recently in other areas such as protein classification and alignment (Haussler, Krogh, Mian & SjOlander, 1992; Baldi, Chauvin, Hunkapiller & McClure, 1993). Practitioners have typically chosen the HMM topology by hand, so that learning the HMM from sample data means estimating only a fixed number of model parameters. The standard approach is to find a maximum likelihood (ML) or maximum a posteriori probability (MAP) estimate of the HMM parameters.

We analyze the "query by committee" algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of thresholded smooth functions.

The attempt to find a single "optimal" weight vector in conventional network training can lead to overfitting and poor generalization. Bayesian methods avoid this, without the need for a validation set, by averaging the outputs of many networks with weights sampled from the posterior distribution given the training data. This sample can be obtained by simulating a stochastic dynamical system that has the posterior as its stationary distribution.

The Bayesian "evidence" approximation has recently been employed to determine the noise and weight-penalty terms used in back-propagation. This paper shows that for neural nets it is far easier to use the exact result than it is to use the evidence approximation. Moreover, unlike the evidence approximation, the exact result neither has to be re-calculated for every new data set, nor requires the running of computer code (the exact result is closed form). In addition, it turns out that the evidence procedure's MAP estimate for neural nets is, in toto, approximation error. Another advantage of the exact analysis is that it does not lead one to incorrect intuition, like the claim that using evidence one can "evaluate different priors in light of the data". This paper also discusses sufficiency conditions for the evidence approximation to hold, why it can sometimes give "reasonable" results, etc.

Matched filtering has been one of the most powerful techniques employed for transient detection. Here we will show that a dynamic neural network outperforms the conventional approach. When the artificial neural network (ANN) is trained with supervised learning schemes there is a need to supply the desired signal for all time, although we are only interested in detecting the transient. In this paper we also show the effects on the detection agreement of different strategies to construct the desired signal. The extension of the Bayes decision rule (011 desired signal), optimal in static classification, performs worse than desired signals constructed by random noise or prediction during the background.

Channel equalization problem is an important problem in high-speed communications. The sequences of symbols transmitted are distorted by neighboring symbols. Traditionally, the channel equalization problem is considered as a channel-inversion operation. One problem of this approach is that there is no direct correspondence between error probability and residual error produced by the channel inversion operation. In this paper, the optimal equalizer design is formulated as a classification problem. The optimal classifier can be constructed by Bayes decision rule. In general it is nonlinear. An efficient hybrid linear/nonlinear equalizer approach has been proposed to train the equalizer. The error probability of new linear/nonlinear equalizer has been shown to be better than a linear equalizer in an experimental channel. 1 INTRODUCTION

The attempt to find a single "optimal" weight vector in conventional networktraining can lead to overfitting and poor generalization. Bayesian methods avoid this, without the need for a validation set, by averaging the outputs of many networks with weights sampled from the posterior distribution given the training data. This sample can be obtained by simulating a stochastic dynamical system that has the posterior as its stationary distribution.

We analyze the "query by committee" algorithm, a method for filtering informativequeries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gainwith positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of thresholded smooth functions.

Channel equalization problem is an important problem in high-speed communications. The sequences of symbols transmitted are distorted by neighboring symbols. Traditionally, the channel equalization problem is considered as a channel-inversion operation. One problem of this approach is that there is no direct correspondence between error probability andresidual error produced by the channel inversion operation. In this paper, the optimal equalizer design is formulated as a classification problem. The optimal classifier can be constructed by Bayes decision rule. In general it is nonlinear. An efficient hybrid linear/nonlinear equalizer approach has been proposed to train the equalizer. The error probability of new linear/nonlinear equalizer has been shown to be better thana linear equalizer in an experimental channel. 1 INTRODUCTION

Matched filtering has been one of the most powerful techniques employed for transient detection. Here we will show that a dynamic neural network outperforms the conventional approach. When the artificial neural network (ANN) is trained with supervised learning schemes there is a need to supply the desired signal for all time, although we are only interested in detecting the transient. In this paper we also show the effects on the detection agreement of different strategies to construct the desired signal. The extension of the Bayes decision rule (011 desired signal), optimal in static classification, performs worse than desired signals constructed by random noise or prediction during the background. 1 INTRODUCTION Detection of poorly defined waveshapes in a nonstationary high noise background is an important and difficult problem in signal processing.