Dataparallel C has been designed for various kinds of architectures and was developed jointly at University of New Hampshire and Oregon State University.
This project dealt with porting the libraries to the nCUBE 2 system and helping a user compile his programs on nCUBE 2 directly from a Sun workstation...
With sequential computing technology reaching its speed limits, parallel processing is emerging as the key to very-high-speed computation. However, developing a parallel program is by no means a simple task; neither is analyzing the performance of parallel programs.
C* is a high-level data-parallel language that hides explicit message passing and...
High level data-parallel languages are easy to use and shield the programmer from machine specific details. A simple and efficient way of providing an interface to such languages is to develop a machine-independent compiler and a routing library, which isolates the low-level machine dependent communication functions, The compiler translates the...
Physical activity recognition using accelerometer data is a rapidly emerging field with many real-world applications. Much of the previous work in this area has assumed that the accelerometer data has already been segmented into pure activities, and the activity recognition task has been to classify these segments. In reality, activity...
This thesis addresses the problem of learning dynamic Bayesian network (DBN) models to support reinforcement learning. It focuses on learning regression tree models of the conditional probability distributions of the DBNs. Existing algorithms presume that the stochasticity in the domain can be modeled as a deterministic function with additive noise....
The Open Modeling Environment (OME) is a tool developed to address some known shortcomings in ecological System Dynamics (SD) modeling research. OME provides a common set of methods for interacting directly with spatial information, reducing the need for modelers to create their own methods for doing so. The environment is...
In real-time control systems, the value of a control decision depends not
only on the correctness of the decision but also on the time when that decision
is available. Recent work in real-time decision making has used machine learning
techniques to automatically construct reactive controllers, that is, controllers
with little...
The thesis focuses on model-based approximation methods for reinforcement
learning with large scale applications such as combinatorial optimization problems.
First, the thesis proposes two new model-based methods to stablize the
value–function approximation for reinforcement learning. The first one is the
BFBP algorithm, a batch-like reinforcement learning process which iterates between...
Probabilistic inference using Bayesian networks is now a well-established approach for reasoning under uncertainty. Among many e ciency-driven tech- niques which have been developed, the Optimal Factoring Problem (OFP) is distinguished for presenting a combinatorial optimization point of view on the problem. The contribution of this thesis is to extend...
We consider the problem of strategic adversarial planning in a Real-Time Strategy (RTS) game. Strategic adversarial planning is the generation of a network of high-level tasks to satisfy goals while anticipating an adversary's actions. In this thesis we describe an abstract state and action space used for planning in an...