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...
Image feature detection and matching are two critical processes for many computer vision tasks. Currently, intensity-based local interest region detectors and local feature-based matching methods are used widely in computer vision applications. But in some applications, such as biological object recognition tasks, within-class changes in pose, lighting, color, and texture...
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....
Automated recognition of object categories in images is a critical step for many real-world computer vision applications. Interest region detectors and region descriptors have been widely employed to tackle the variability of objects in pose, scale, lighting, texture, color, and so on. Different types of object recognition problems usually require...
Knowledge workers are struggling in the information flood. There is a growing interest in intelligent desktop environments that help knowledge workers organize their daily life. Intelligent desktop environments allow the desktop user to define a set of “activities” that characterize the user’s desktop work. These environments then attempt to identify...
With edge rates of high speed digital devices pushing into the sub-nano second
range, interconnections with the associated packages play a major role in determining
the speed, size and performance of digital circuits and systems. The purpose of this
study is to develop experimental techniques based on time domain peeling...
In wood-based composites, the glue-line (interface) between wood-strands affects the stress transfer from one member to the next. The glue-line properties determine the rate of load transfer between phases and these properties depend on wood species, surface preparation, glue properties, glue penetration into wood cells, and moisture content of the...
In this thesis, A nonlinear methodology for the control of the highly
maneuverable, high performance aircraft HARV (F-18) is studied by using sliding-mode
control (SMC). This control law, which takes a continuous function when the
input constraints are not considered, satisfies the reachability condition by which
concerned states are driven...
Many important application problems in engineering can be formalized as nonlinear
optimization tasks. However, numerical methods for solving such problems
are brittle and do not scale well. For example, these methods depend critically
on choosing a good starting point from which to perform the optimization search.
In high-dimensional spaces, numerical...
Markov Decision Process (MDP) is a well-known framework for devising the optimal decision making strategies under uncertainty. Typically, the decision maker assumes a stationary environment which is characterized by a time-invariant transition probability matrix. However, in many real-world scenarios, this assumption is not justified, thus the optimal strategy might not...