Genre
The Observer-Observation Dilemma in Neuro-Forecasting
Zimmermann, Hans-Georg, Neuneier, Ralph
We explain how the training data can be separated into clean information andunexplainable noise. Analogous to the data, the neural network is separated into a time invariant structure used for forecasting, and a noisy part. We propose a unified theory connecting the optimization algorithms forcleaning and learning together with algorithms that control the data noise and the parameter noise. The combined algorithm allows a data-driven local control of the liability of the network parameters and therefore an improvement in generalization. The approach is proven to be very useful at the task of forecasting the German bond market.
Reinforcement Learning with Hierarchies of Machines
Parr, Ronald, Russell, Stuart J.
We present a new approach to reinforcement learning in which the policies consideredby the learning process are constrained by hierarchies of partially specified machines. This allows for the use of prior knowledge to reduce the search space and provides a framework in which knowledge can be transferred across problems and in which component solutions can be recombined to solve larger and more complicated problems. Our approach can be seen as providing a link between reinforcement learning and"behavior-based" or "teleo-reactive" approaches to control. We present provably convergent algorithms for problem-solving and learning withhierarchical machines and demonstrate their effectiveness on a problem with several thousand states.
Modeling Acoustic Correlations by Factor Analysis
Saul, Lawrence K., Rahim, Mazin G.
Hidden Markov models (HMMs) for automatic speech recognition rely on high dimensional feature vectors to summarize the shorttime propertiesof speech. Correlations between features can arise when the speech signal is non-stationary or corrupted by noise. We investigate how to model these correlations using factor analysis, a statistical method for dimensionality reduction. Factor analysis uses a small number of parameters to model the covariance structure ofhigh dimensional data. These parameters are estimated by an Expectation-Maximization (EM) algorithm that can be embedded inthe training procedures for HMMs.
Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction
Willett, Daniel, Rigoll, Gerhard
In this paper, we present a novel hybrid architecture for continuous speech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is used as a preprocessor that takes several frames of the feature vector as input to produce more discriminative featurevectors with respect to the underlying HMM system. This hybrid system is an extension of a state-of-the-art continuous HMM system, andin fact, it is the first hybrid system that really is capable ofoutperforming thesestandard systems with respect to the recognition accuracy. Experimental results show an relative error reduction of about 10% that we achieved on a remarkably good recognition system based on continuous HMMsfor the Resource Management 1OOO-word continuous speech recognition task.
Globally Optimal On-line Learning Rules
We present a method for determining the globally optimal online learning rule for a soft committee machine under a statistical mechanics framework. This work complements previous results on locally optimal rules, where only the rate of change in generalization the total reduction inerror was considered. We maximize the whole learning process and show howgeneralization error over the resulting rule can significantly outperform the locally optimal rule. 1 Introduction We consider a learning scenario in which a feed-forward neural network model (the an unknown mapping (the teacher), given a set of training examplesstudent) emulates The performance of the student network is typicallyproduced by the teacher. A common form of training is online learning, where training patterns are presented sequentially and independently to the network at each learning step. This form of training can be beneficial in terms of both storage and computation time, especially for large systems.
Phase Transitions and the Perceptual Organization of Video Sequences
Estimating motion in scenes containing multiple moving objects remains a difficult problem in computer vision. A promising approach tothis problem involves using mixture models, where the motion of each object is a component in the mixture. However, existing methodstypically require specifying in advance the number of components in the mixture, i.e. the number of objects in the scene.
Active Data Clustering
Hofmann, Thomas, Buhmann, Joachim M.
Active data clustering is a novel technique for clustering of proximity datawhich utilizes principles from sequential experiment design in order to interleave data generation and data analysis. The proposed activedata sampling strategy is based on the expected value of information, a concept rooting in statistical decision theory. This is considered to be an important step towards the analysis of largescale datasets, because it offers a way to overcome the inherent data sparseness of proximity data.
Learning to Schedule Straight-Line Code
Moss, J. Eliot B., Utgoff, Paul E., Cavazos, John, Precup, Doina, Stefanovic, Darko, Brodley, Carla E., Scheeff, David
Program execution speed on modem computers is sensitive, by a factor of two or more, to the order in which instructions are presented to the processor. Torealize potential execution efficiency, an optimizing compiler must employ a heuristic algorithm for instruction scheduling. Such algorithms are painstakingly handcrafted, which is expensive and time-consuming. We show how to cast the instruction scheduling problem as a learning task, obtaining theheuristic scheduling algorithm automatically. Our focus is the narrower problem of scheduling straight-line code (also called basic blocks of instructions). Our empirical results show that just a few features are adequate forquite good performance at this task for a real modem processor, and that any of several supervised learning methods perform nearly optimally withrespect to the features used.
A Generic Approach for Identification of Event Related Brain Potentials via a Competitive Neural Network Structure
Lange, Daniel H., Siegelmann, Hava T., Pratt, Hillel, Inbar, Gideon F.
We present a novel generic approach to the problem of Event Related Potential identification and classification, based on a competitive Neural Netarchitecture. The network weights converge to the embedded signal patterns, resulting in the formation of a matched filter bank. The network performance is analyzed via a simulation study, exploring identification robustness under low SNR conditions and compared to the expected performance from an information theoretic perspective. The classifier is applied to real event-related potential data recorded during a classic oddball type paradigm; for the first time, withinsession variablesignal patterns are automatically identified, dismissing the strong and limiting requirement of a-priori stimulus-related selective grouping of the recorded data.