We propose an online learning algorithm for large margin training of continuous density hidden Markov models. The online algorithm updates the model parameters incrementally after the decoding of each training utterance. For large margin training, the algorithm attempts to separate the log-likelihoods of correct and incorrect transcriptions by an amount proportional to their Hamming distance. W...

We introduce lightly supervised learning for dependency parsing. In this paradigm, the algorithm is initiated with a parser, such as one that was built based on a very limited amount of fully annotated training data. Then, the algorithm iterates over unlabeled sentences and asks only for a single bit of feedback, rather than a full parse tree. Specifically, given an example the algorithm output...

This paper reports the study results on neural network training algorithm of numerical optimization techniques multiface detection in static images. The training algorithms involved are scale gradient conjugate backpropagation, conjugate gradient backpropagation with Polak-Riebre updates, conjugate gradient backpropagation with Fletcher-Reeves updates, one secant backpropagation and resilent ba...

This paper presents a training model for Elman recurrent neural networks, based on evolutionary algorithms. The proposed evolutionary algorithms are classic genetic algorithms, the multimodal clearing algorithm and the CHC algorithm. These training algorithms are compared in order to assess the effectiveness of each training model when predicting Spanish autonomous indebtedness.

In this paper, we investigate training artificial neural networks to ride simulated motorbikes in a new computer game using two different training techniques, Evolutionary Algorithms and the Backpropagation Algorithm. We show that the backpropagation algorithm creates a rider which is faster than that created by the evolutionary algorithm but at the price of requiring a training set created by ...

Adaptive equalization is an accepted method to mitigate the Inter-Symbol Interference (ISI) in wireless communication. Frequently, adaptive algorithm must needs transmission of well-known training sequence to track the time varying characteristics of the channel and hence make the most of superfluous bandwidth. It is also not viable to have training sequences in all types of transmissions (e. g...

In this paper a new algorithm is proposed for fast discriminative training of hidden Markov models (HMMs) based on minimum classification error (MCE). The algorithm is able to train acoustic models in a few iterations, thus overcoming the slow training speed typical of discriminative training methods based on gradient-descendent. The algorithm tries to cancel the gradient of the objective funct...

This paper presents a novel training algorithm for adaptive neuro-fuzzy inference systems. The algorithm combines the Error Backpropagation (EBP) algorithm with Variable Structure Systems (VSS) approach. Expressing the parameter update rule as a dynamic system in continuous time and applying sliding mode control (SMC) methodology to the dynamic model of the gradient based training procedure res...