In this paper, we introduce a fast estimate algorithm for discriminant training of semi-continuous HMM (Hidden Markov Models). We first present the Frame Discrimination (FD) method proposed in [9] for weight re-estimate. Then, the weight update equation is formulated in the specific framework of semi-continuous models. Finally, we propose an approximated update function which requires a very lo...

Discriminative training techniques for Hidden Markov Models were recently proposed and successfully applied for automatic speech recognition In this paper a discussion of the Minimum Classi cation Error and the Maximum Mu tual Information objective is presented An extended reesti mation formula is used for the HMM parameter update for both objective functions The discriminative training me thod...

Multilayer perceptrons are often trained using error backpropagation (BP). BP training can be done in either a batch or continuous manner. Claims have frequently been made that batch training is faster and/or more "correct" than continuous training because it uses a better approximation of the true gradient for its weight updates. These claims are often supported by empirical evidence on very s...

OBJECTIVE To evaluate the feasibility of free-living walking training in type 2 diabetic patients and to investigate the effects of interval-walking training versus continuous-walking training upon physical fitness, body composition, and glycemic control. RESEARCH DESIGN AND METHODS Subjects with type 2 diabetes were randomized to a control (n = 8), continuous-walking (n = 12), or interval-wa...

Despite recent improvements in training methodology, discrete latent variable models have failed to achieve the performance and popularity of their continuous counterparts. Here, we evaluate several approaches to training large-scale image models on CIFAR-10 using a probabilistic variant of the recently proposed Vector Quantized VAE architecture. We find that biased estimators such as continuou...