John Moody, Lizhong Wu, Yuansong Liao, Matthew Saffell
the Founder and President of Nonlinear Prediction Systems, a company specializing in the development of forecasting and trading systems. Moody is a past General Chair and Program Chair of the Neural...
Alan W Black, Ralf D. Brown, Robert Frederking, Rita Singh, John Moody, Eric Steinbrecher
We carried out a one-year project to build a portable speech-tospeech translation system in a new language that could run on a small portable computer. Croatian was chosen as the target language. The...
RAPID DEVLOPEMENT OF SPEECH-TO-SPEECH TRANSLATION SYSTEMS (2007)
Alan W Black, Ralf D. Brown, Robert Frederking, Kevin Lenzo, John Moody, Er Rudnicky, ...
This paper describes building of the basic components, particularly speech recognition and synthesis, of a speech-tospeech translation system. This work is described within the framework of the...
Stochastic direct reinforcement: Application to simple games with recurrence (2004)
John Moody, Yufeng Liu, Matthew Saffell, Kyoungju Youn
We investigate repeated matrix games with stochastic players as a microcosm for studying dynamic, multi-agent interactions using the Stochastic Direct Reinforcement (SDR) policy gradient algorithm....
testing the tongues speech-to-speech machine translation system (2002)
Robert E. Frederking, Alan W Black, Ralf D. Brown, John Moody, Eric Steinbrecher
The Tongues portable, rapid-development, speech-to-speech machine translation system was developed specifically to allow a realistic field-test of a deployable prototype. In this paper we will...
Tongues: Rapid development of a speech-to-speech translation system (2002)
Alan W Black, Ralf D. Brown, Robert Frederking, Rita Singh, John Moody, Eric Steinbrecher
We carried out a one-year project to build a portable speech-tospeech translation system in a new language that could run on a small portable computer. Croatian was chosen as the target language. The...
Tongues: Rapid development of a speech-to-speech translation system (2002)
Alan W Black, Ralf D. Brown, Robert Frederking, Rita Singh, John Moody, Eric Steinbrecher
We carried out a one-year project to build a portable speech-tospeech translation system in a new language that could run on a small portable computer. Croatian was chosen as the target language. The...
Tongues: Rapid development of a speech-to-speech translation system (2002)
Alan W Black, Ralf D. Brown, Robert Frederking, Rita Singh, John Moody, Eric Steinbrecher
We carried out a one-year project to build a portable speech-tospeech translation system in a new language that could run on a small portable computer. Croatian was chosen as the target language. The...
Neural Network Models for the Blood Glucose Metabolism of a Diabetic (1999)
Volker Tresp, Thomas Briegel, John Moody
We study the application of neural networks to modeling the blood glucose metabolism of a diabetic. In particular we consider recurrent neural networks and time series convolution neural networks...
Feature Selection Based on Joint Mutual Information (1999)
A feature/input selection method is proposed based on joint mutual information. The new method is better than the existing methods based on mutual information in eliminating redundancy in the inputs....
Term Structure of Interactions of Foreign Exchange Rates (1999)
this paper, we investigate the term structure of the interactions of multiple foreign exchange price movements for a set of seven major exchange rates. The techniques used include a causal...
Data Visualization and Feature Selection: New Algorithms for Nongaussian Data (1999)
Data visualization and feature selection methods are proposed based on the joint mutual information and ICA. The visualization methods can find many good 2-D projections for high dimensional data...
Neural Network Models for the Blood Glucose Metabolism of a Diabetic (1999)
Volker Tresp, Thomas Briegel, John Moody
2 NEURAL NETWORK MODELS FOR THE BLOOD GLUCOSE METABOLISM OF A DIABETIC We study the application of neural networks to modeling the blood glucose metabolism of a diabetic. In particular we consider...
A Smoothing Regularizer for Feedforward and Recurrent Neural Networks (1996)
We derive a smoothing regularizer for dynamic network models by requiring robustness in prediction performance to perturbations of the training data. The regularizer can be viewed as a generalization...
Improved Estimates For The Rescaled Range And Hurst Exponents (1996)
Rescaled Range R=S analysis and Hurst Exponents are widely used as measures of long-term memory structures in stochastic processes. Our empirical studies show, however, that these statistics can...
Feedback Control of Petri Nets Based on Place Invariants (1996)
Katerina Yamalidou, John Moody, Michael Lemmon, Panos Antsaklis
This report describes a method for constructing a Petri net controller for a discrete event system modeled by a Petri net. The controller consists only of places and arcs and is computed based on the...
John Wiley, John Moody, Joachim Utans
We propose strategies for selecting a good neural network architecture for modeling any specific data set. Our approach involves efficiently searching the space of possible architectures and...
Economic Forecasting: Challenges and Neural Network Solutions (1995)
Macroeconomic forecasting is a very difficult task due to the lack of an accurate, convincing model of the economy. The most accurate models for economic forecasting, "black box" time...
Economic forecasting: Challenges and neural network solutions (1995)
Macroeconomic forecasting is a very difficult task due to the lack of an accurate, convincing model of the economy. The most accurate models for economic forecasting, “black box ” time series...
Prediction risk and architecture selection for neural networks (1994)
Abstract. We describe two important sets of tools for neural network modeling: prediction risk estimation and network architecture selection. Prediction risk is defined as the expected performance of...
Prediction Risk and Architecture Selection for Neural Networks (1994)
. We describe two important sets of tools for neural network modeling: prediction risk estimation and network architecture selection. Prediction risk is defined as the expected performance of an...
A Trivial but Fast Reinforcement Controller (1994)
We compare simulation results for the classic Barto-Sutton-Anderson pole balancer (which uses the Michie and Chambers "boxes" representation) with results for a reinforcement learning...
Prediction Risk and Architecture Selection for Neural Networks (1994)
. We describe two important sets of tools for neural network modeling: prediction risk estimation and network architecture selection. Prediction risk is defined as the expected performance of an...
Prediction risk and architecture selection for neural networks (1994)
Abstract. We describe two important sets of tools for neural network modeling: prediction risk estimation and network architecture selection. Prediction risk is defined as the expected performance of...
Predicting the U.S. Index of Industrial Production (Extended Abstract) (1993)
John Moody, Uzi Levin, Steve Rehfuss
) John Moody, Uzi Levin, and Steve Rehfuss Introduction Of great interest to forecasters of the economy is predicting the "business cycle", or the overall level of economic activity. The...
Learning Rate Schedules For Faster Stochastic Gradient Search (1992)
Christian Darken, Joseph Chang, Joseph Chang Z, John Moody
. Stochastic gradient descent is a general algorithm that includes LMS, on-line backpropagation, and adaptive k-means clustering as special cases. The standard choices of the learning rate j (both...
The notion of generalization can be defined precisely as the prediction risk, the expected performance of an estimator on new observations. In this paper, we propose the prediction risk as a measure...