TRLA - Tandem Repeat Locator Algorithm
This project involves developing software tools for locating repetitive regions within DNA sequences,
known as tandem repeats. Tandem repeats are not perfect when they occur in DNA sequences. There are two main
types of imperfections: substitutions and indels (an insertion or deletion). We have used dynamic programming with wraparound (Wraparound Dynamic Programming)
to locate all tandem repeats, regardless of imperfections.
Modeling User Preferences via Theory Refinement (KBANN)
We present an approach to encoding of soft assumptions using a knowledge based neural network(KBANN) technique.
We show how to encode assumptions concerning preferential independence and monotonicity as Horn-clauses and how to encode these
in a KBANN network. We empirically compare the KBANN network with an unbiased ANN in
terms of learning rate and accuracy for preference structures consistent and inconsistent
with the domain theory.
Learning from Reinforcements (Q-Learning)
We look at the task of learning from reinforcements. One-step connectionist (neural network)
Q-Learning was implemented to act as a controller for the agent GeislerPlayer in the AgentWorld program.
The backpropogation algorithm is used as the policy function.