Teaching an Old Robot New Tricks: Learning Novel Tasks via Interaction with People and Things

As AI has begun to reach out beyond its symbolic, objectivist roots into the embodied, experientialist realm, many projects are exploring different aspects of creating machines which interact with and respond to the world as humans do. Techniques for visual processing, object recognition, emotional response, gesture production and recognition, etc., are necessary components of a complete humanoid robot. However, most projects invariably concentrate on developing a few of these individual components, neglecting the issue of how all of these pieces would eventually fit together. The focus of the work in this dissertation is on creating a framework into which such specific competencies can be embedded, in a way that they can interact with each other and build layers of new functionality. To be of any practical value, such a framework must satisfy the real-world constraints of functioning in real-time with noisy sensors and actuators. The humanoid robot Cog provides an unapologetically adequate platform from which to take on such a challenge. This work makes three contributions to embodied AI. First, it offers a general-purpose architecture for developing behavior-based systems distributed over networks of PC's. Second, it provides a motor-control system that simulates several biological features which impact the development of motor behavior. Third, it develops a framework for a system which enables a robot to learn new behaviors via interacting with itself and the outside world. A few basic functional modules are built into this framework, enough to demonstrate the robot learning some very simple behaviors taught by a human trainer. A primary motivation for this project is the notion that it is practically impossible to build an "intelligent" machine unless it is designed partly to build itself. This work is a proof-of-concept of such an approach to integrating multiple perceptual and motor systems into a complete learning agent.

Learning Commonsense Categorical Knowledge in a Thread Memory System

If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that we humans have about the world. This endeavor suggests steps such as identifying the kinds of knowledge people commonly have about the world, constructing suitable knowledge representations, and exploring the mechanisms that people use to make judgments about the everyday world. In this work, I contribute to these goals by proposing an architecture for a system that can learn commonsense knowledge about the properties and behavior of objects in the world. The architecture described here augments previous machine learning systems in four ways: (1) it relies on a seven dimensional notion of context, built from information recently given to the system, to learn and reason about objects' properties; (2) it has multiple methods that it can use to reason about objects, so that when one method fails, it can fall back on others; (3) it illustrates the usefulness of reasoning about objects by thinking about their similarity to other, better known objects, and by inferring properties of objects from the categories that they belong to; and (4) it represents an attempt to build an autonomous learner and reasoner, that sets its own goals for learning about the world and deduces new facts by reflecting on its acquired knowledge. This thesis describes this architecture, as well as a first implementation, that can learn from sentences such as ``A blue bird flew to the tree'' and ``The small bird flew to the cage'' that birds can fly. One of the main contributions of this work lies in suggesting a further set of salient ideas about how we can build broader purpose commonsense artificial learners and reasoners.

Learning Linear, Sparse, Factorial Codes

In previous work (Olshausen & Field 1996), an algorithm was described for learning linear sparse codes which, when trained on natural images, produces a set of basis functions that are spatially localized, oriented, and bandpass (i.e., wavelet-like). This note shows how the algorithm may be interpreted within a maximum-likelihood framework. Several useful insights emerge from this connection: it makes explicit the relation to statistical independence (i.e., factorial coding), it shows a formal relationship to the algorithm of Bell and Sejnowski (1995), and it suggests how to adapt parameters that were previously fixed.

Implementation Workshop: High Performance Work Organizations

Since the rise of the industrial revolution, there are few challenges that compare in scale and scope with the challenge of implementing lean principles in order to achieve high performance work systems. This report summarize key insights and learning by representatives from a cross section of organizations who are on this journey. Specifically, we report on findings from the first Lean Aircraft Initiative (LAI) Implementation Workshop, which was held on February 5-6, 1997.

Implementation Workshop: High Performance Work Organizations

Since the rise of the industrial revolution, there are few challenges that compare in scale and scope with the challenge of implementing lean principles in order to achieve high performance work systems. This report summarize key insights and learning by representatives from a cross section of organizations who are on this journey. Specifically, we report on findings from the first Lean Aircraft Initiative (LAI) Implementation Workshop, which was held on February 5-6, 1997. The report is not a “cookbook” or a “how to” manual. Rather, it is a summary of the first phase in a learning process. It is designed to codify lessons learning, facilitate diffusion among people not at the session, and set the stage for further learning about implementation.

Gestión de la actividad no presencial y autoevaluación de competencias = Management of student learning outside the classroom and the self-evaluation of competences

La asignatura troncal “Evaluación Psicológica” de los estudios de Psicología y del estudio de grado “Desarrollo humano en la sociedad de la información” de la Universidad de Girona consta de 12 créditos según la Ley Orgánica de Universidades. Hasta el año académico 2004-05 el trabajo no presencial del alumno consistía en la realización de una evaluación psicológica que se entregaba por escrito a final de curso y de la cual el estudiante obtenía una calificación y revisión si se solicitaba. En el camino hacia el Espacio Europeo de Educación Superior, esta asignatura consta de 9 créditos que equivalen a un total de 255 horas de trabajo presencial y no presencial del estudiante. En los años académicos 2005-06 y 2006-07 se ha creado una guía de trabajo para la gestión de la actividad no presencial con el objetivo de alcanzar aprendizajes a nivel de aplicación y solución de problemas/pensamiento crítico (Bloom, 1975) siguiendo las recomendaciones de la Agencia para la Calidad del Sistema Universitario de Cataluña (2005). La guía incorpora: los objetivos de aprendizaje, los criterios de evaluación, la descripción de las actividades, el cronograma semanal de trabajos para todo el curso, la especificación de las tutorías programadas para la revisión de los diversos pasos del proceso de evaluación psicológica y el uso del foro para el conocimiento, análisis y crítica constructiva de las evaluaciones realizadas por los compañeros

Multidimensional Adaptations for Open Learning Management Systems

Our work is focused on alleviating the workload for designers of adaptive courses on the complexity task of authoring adaptive learning designs adjusted to specific user characteristics and the user context. We propose an adaptation platform that consists in a set of intelligent agents where each agent carries out an independent adaptation task. The agents apply machine learning techniques to support the user modelling for the adaptation process

Towards Direct Policy Search Reinforcement Learning for Robot Control

This paper proposes a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, when using RL, has been to apply value function based algorithms, the system here detailed is characterized by the use of direct policy search methods. Rather than approximating a value function, these methodologies approximate a policy using an independent function approximator with its own parameters, trying to maximize the future expected reward. The policy based algorithm presented in this paper is used for learning the internal state/action mapping of a behavior. In this preliminary work, we demonstrate its feasibility with simulated experiments using the underwater robot GARBI in a target reaching task

Designing context-aware adaptive units of learning based on IMS-LD standard

Learning contents adaptation has been a subject of interest in the research area of the adaptive hypermedia systems. Defining which variables and which standards can be considered to model adaptive content delivery processes is one of the main challenges in pedagogical design over e-learning environments. In this paper some specifications, architectures and technologies that can be used in contents adaptation processes considering characteristics of the context are described and a proposal to integrate some of these characteristics in the design of units of learning using adaptation conditions in a structure of IMS-Learning Design (IMS-LD) is presented. The key contribution of this work is the generation of instructional designs considering the context, which can be used in Learning Management Systems (LMSs) and diverse mobile devices

Curriculum sequencing for an e-learning system based on learning styles

This work shows the use of adaptation techniques involved in an e-learning system that considers students' learning styles and students' knowledge states. The mentioned e-learning system is built on a multiagent framework designed to examine opportunities to improve the teaching and to motivate the students to learn what they want in a user-friendly and assisted environment

Ventajas que aporta el E-Learning a los procesos de diferenciación estratégica e internacionalización en la Universidad Del Rosario

En el presente trabajo se analiza la existencia y argumenta la importancia de las ventajas que aporta el E-Learning al proceso de Internacionalización en la Universidad del Rosario, además se indaga si dichas ventajas podrían facilitar la diferenciación estratégica de la misma. Inicia con una revisión teórica sobre los conceptos de educación virtual y aprendizaje, y su estado actual en Colombia, logrando la creación de un marco teórico. En una segunda etapa se identificarán las características que comparte la institución educativa con una organización y que la hacen objeto de estudio en el campo estratégico, específicamente en cuanto a la diferenciación. Posteriormente se describirán las etapas de implementación del E-Learning en la Universidad, analizando los aspectos más importantes de este proceso. Más adelante se hace una aproximación al concepto de internacionalización y la importancia que tiene en el mundo multicultural actual. Finalmente se relacionan las ventajas de la implementación del E-Learning con las brindadas en el proceso de internacionalización y se argumenta si estas facilitan la diferenciación estratégica del Rosario.

Aula de música : desarrollo de contenidos en una herramienta de e-learning para la asignatura de música en Educación Primaria.

Aula de música es una herramienta e-learning para el desarrollo del aprendizaje de la música para niños con edades comprendidas entre los 6 y 12 años, edades correspondientes a las de los alumnos de la etapa de la Educación Primaria. En esta herramienta destaca el uso de estándares y especificaciones como LOM, IMS, etc. que van a facilitar la tarea de reutilizar la documentación incluida para compartir conocimiento. El proceso de elaboración del contenido ha sido fundamental y en relación con el entorno de trabajo debe mencionarse que se ha primado la construcción de una GUI que sirva para aprender y que motive a los alumnos a aprender música de una forma diferente, en contraposición a realizar una diseño estético que fuera incapaz de adaptarse a las capacidades de cada tipo de usuario, para lo que se han tenido en cuenta criterios de usabilidad y accesibilidad (WAI).

Technology Enhanced Learning Guide

Technology is changing how students learn and how we research. Perhaps you want to use technology to enhance communication or improve student support. You may want create a distance learning activity, a flexibly delivered module or indeed a whole course. You may simply want to find out where to find authoritative information, or to see what support exists for this type of work. The University is committed to delivering high quality learning and teaching, using technology where appropriate, in order to offer a distinctive Southampton educational experience. Technology Enhanced Learning (TEL), also known as e‑learning, is becoming increasingly important to students, teaching staff and the institution. This guide highlights some of the most important matters to consider. It is intended to help you to tackle the key issues that determine the success of TEL projects and to work on those projects in a considered way. Written with the input of colleagues from around the University, it prompts you to ask important questions and points you to sources of up-to-date knowledge and advice. Technology changes rapidly. This guide is about managing the work in a practical way. The University supports the use of a variety of TEL approaches for teaching and learning and colleagues are ready to offer their experience and advice. Each person has distinctive skills and specific experiences. No single person will have all the answers you are looking for. Be ready to investigate alternative approaches that suit you and your students’ needs in different ways. - Madeline Paterson, University of Southampton

La sabiduría como competencia gerencial

Aunque el concepto de sabiduría ha sido ampliamente estudiado por expertos de áreas como la filosofía, la religión y la psicología, aún enfrenta limitaciones en cuanto a su definición y evaluación. Por esto, el presente trabajo tiene como objetivo, formular una definición del concepto de sabiduría que permita realizar una propuesta de evaluación del concepto como competencia en los gerentes. Para esto, se realizó un análisis documental de tipo cualitativo. De esta manera, se analizaron diversos textos sobre la historia, las definiciones y las metodologías para evaluar tanto la sabiduría como las competencias; diferenciando la sabiduría de otros constructos y analizando la diferencia entre las competencias generales y las gerenciales para posteriormente, definir la sabiduría como una competencia gerencial. Como resultado de este análisis se generó un prototipo de prueba denominado SAPIENS-O, a través del cuál se busca evaluar la sabiduría como competencia gerencial. Como alcances del instrumento se pueden identificar la posibilidad de medir la sabiduría como competencia en los gerentes, la posibilidad de dar un nuevo panorama a las dificultades teóricas y empíricas sobre la sabiduría y la posibilidad de facilitar el estudio de la sabiduría en ambientes reales, más específicamente en ambientes organizacionales.

El paradigma del Desarrollo Urbano Sostenible -DUS- como referente del proceso de toma de decisiones legislativas en Colombia. Análisis de la agenda legislativa del Congreso de la República entre 1991 y 2006

Este trabajo contribuye al análisis de la incidencia del paradigma del Desarrollo Urbano Sostenible en el proceso de toma de decisiones legislativas en Colombia, concentrándose en la discusión y definición de la agenda legislativa sobre asuntos urbanos, durante el periodo 1991-2006.