Improved neural network scatterometer forward models

Improved Neural Network Scatterometer

Current retrieval methods for wind vectors from scatterometer observations over the ocean surface requires a sensor model relating the measured backscatter to the wind vector. The complexity of the problem and the lack of reliable measurements mean that models based on the analytical solution of the physical equations is impossible. Thus an empirical approach, such as implemented in the operati...

Improved Multi-beam Neural Network Scatterometer Forward Models NCRG/2000/008

Improved probability estimation with neural network models

Wei Wei, Etienne Barnard and Mark Fanty Center for Spoken Language Understanding Oregon Graduate Institute of Science and Technology 20000 N.W.Walker Road, Portland, OR 97291-1000 ABSTRACT Neural network classi ers can provide outputs that estimate Bayesian posterior probabilities under the assumptions that an in nite amount of training data are available, the network is su ciently complex and ...

Signal Prediction by Layered Feed - Forward Neural Network (RESEARCH NOTE).

In this paper a nonparametric neural network (NN) technique for prediction of future values of a signal based on its past history is presented. This approach bypasses modeling, identification, and parameter estimation phases that are required by conventional parametric techniques. A multi-layer feed forward NN is employed. It develops an internal model of the signal through a training operation...

Feed forward pre-training for recurrent neural network language models

The recurrent neural network language model (RNNLM) has been demonstrated to consistently reduce perplexities and automatic speech recognition (ASR) word error rates across a variety of domains. In this paper we propose a pre-training method for the RNNLM, by sharing the output weights of the feed forward neural network language model (NNLM) with the RNNLM. This is accomplished by first fine-tu...