We present a novel approach to learning predictive sequential models, called similarity-based alignment and generalization, which incorporates in the induction process a specific form of domain knowledge derived from a similarity metric of the points in the input space. When applied to Hidden Markov Models, our framework yields a new class of learning algorithms called SimAlignGen. We discuss t...

We have extended behavior trees to support a form of casebased reasoning by retrieving the best action to be performed according to the current state of the game. The case based was filled by programming by demonstration techniques. In this paper we demonstrate how this extension can be used to program the behavior of a non-player character in a complex 3D video game. We have also measured the ...

The paper uses mesoscopic, non-linear lattice dynamics based (Peyrard-Bishop-Dauxois, PBD) modeling to describe thermal properties of DNA below and near the denaturation temperature. Computationally efficient notation is introduced for the relevant statistical mechanics. Computed melting profiles of long and short heterogeneous sequences are presented, using a recently introduced reparametrizat...

We present a new visual programming language and environment that serves as a form of feedback and representation in a Programming by Demonstration system. The language differs from existing visual languages because it explicitly represents data objects and implicitly represents operations by changes in data objects. The system was designed to provide non-programmers with programming support fo...

The decision-making by agents in games is commonly based on reinforcement learning. To improve the quality of agents, it is necessary to solve the problems of the time and state space that are required for learning. Such problems can be solved by Macro-Actions, which are defined and executed by a sequence of primitive actions. In this line of research, the learning time is reduced by cutting do...

Vincent Aleven Intelligent tutoring systems (ITS) are highly effective in supporting student learning, but are difficult to build. The Cognitive Tutor Authoring Tools (CTAT) project started over 6 years ago with the goals of making it easier for experienced programmers, and possible for non-programmers to create an ITS. CTAT supports tutor building through programming by demonstration, an appro...

We are proposing a supervised learning approach in robot force control which enables robot programming by demonstration through an operator. The learning element of the controller is based on a neural network prestructured to represent knowledge in terms of rules. Tasks are demonstrated in a virtual environment. Visual feedback using sensor ball devices and graphic display of forces as well as ...

Robust methods for representing, generalizing, and sharing knowledge across various robotics systems and configurations are important in many domains of robotics research and application. In this paper we present a method for modeling tasks and robot skills to simplify the programming and reuse of knowledge between robots in manufacturing environments. Specifically, we propose an assembly taxon...

We present three descriptors of texture feature of a region. Namely, the homogeneous texture descriptor (HTD), the edge histogram descriptor (EHD), and the perceptual browsing descriptor (PBD). They are currently included in the Committee Draft of the MPEG-7 Visual (ISO/IEC 15938-3). Each descriptor has a unique functionality and application domain. HTD and EHD describe statistical distribution...