Learning Deterministic Finite Automata (DFA) is a hard task that has been much studied within machine learning and evolutionary computation research. This paper presents a new met...
The “JavaTM Intelligent Tutoring System” (JITS) research project involves the development of a programming tutor designed for students in their first programming course in Jav...
The genetic programming (GP) paradigm is a new approach to inductively forming programs that describe a particular problem. The use of natural selection based on a fitness ]unction...
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Often when modeling structured domains, it is desirable to leverage information that is not naturally expressed as simply a label. Examples include knowledge about the evaluation ...