Learning from human teaching strategies

Recent works in the area of adaptive education systems point out the importance of aumenting the student model to improve the personalization and adaptation to the learner by means of several aspects such as emotions, user locations or interactions. Until now the study of interactions has been mainly focused on the student-learning system flow, despite the fact that the most successful and used way of teaching are the traditional face-to-face interactions. In this project, we explore the use of interactions among teachers and students, as they occur in traditional education, to enrich the current student models, with the aim of providing them with useful information about new characteristics for improving the learning process. At a first step, in this paper we present the formal process carried out to obtain information about teachers’ expertise and necessities regarding the direct interactions with students.

Chelmsford College: Full circle – using systems integration to enhance observation, appraisal and CPD

Chelmsford College has created an observation, appraisal and continuing professional development (CPD) cycle by successfully integrating a collection of bespoke web-based systems together within its intranet. Students have benefitted from improved teaching and learning because of the rapid, transparent and thorough cycle of staff being observed, appraised and given appropriate CPD. The College has also saved time and money by being able to use single-source data to schedule observations, appraisals and CPD to individuals' needs.

Alliance Learning: Revolutionising the way they work with an online learner management system

Since May 2012 Paul Cocker, Operation Executive and the Senior Management Team of Alliance Learning have introduced an online learner management system for every learner, requiring significant investment in systems, hardware, acceptance by staff and above all, time and commitment from the management team. This organisation has taken the radical step to overcome one of the major barriers to achieve its goal by dedicating three periods of two weeks where the business has closed for staff CPD training. A total of 500 man hours were invested to implement the online system. This is an excellent model of how to make these major changes effective in the shortest time.

An Open and Social Spaced Repetition System for Language Learning

In the last decades big improvements have been done in the field of computer aided learning, based on improvements done in computer science and computer systems. Although the field has been always a bit lagged, without using the latest solutions, it has constantly gone forward taking profit of the innovations as they show up. As long as the train of the computer science does not stop (and it won’t at least in the near future) the systems that take profit of those improvements will not either, because we humans will always need to study; Sometimes for pleasure and some other many times out of need. Not all the attempts in the field of computer aided learning have been in the same direction. Most of them address one or some few of the problems that show while studying and don’t take into account solutions proposed for some other problems. The reasons for this can be varied. Sometimes the solutions simply are not compatible. Some other times, because the project is an investigation it’s interesting to isolate the problem. And, in commercial products, licenses and patents often prevent the new projects to use previous work. The world moved forward and this is an attempt to use some of the options offered by technology, mixing some old ideas with new ones.

Dialog Systems based on Markov decision processes over two real tasks

In this work the state of the art of the automatic dialogue strategy management using Markov decision processes (MDP) with reinforcement learning (RL) is described. Partially observable Markov decision processes (POMDP) are also described. To test the validity of these methods, two spoken dialogue systems have been developed. The first one is a spoken dialogue system for weather forecast providing, and the second one is a more complex system for train information. With the first system, comparisons between a rule-based system and an automatically trained system have been done, using a real corpus to train the automatic strategy. In the second system, the scalability of these methods when used in larger systems has been tested.

Case study: Digital learning assets for engineering

Case study on how Furness College are collaborating with BAE Systems to co-develop an interactive learning package to support the delivery of the performing engineering operations qualification.

Contributions to unsupervised and supervised learning with applications in digital image processing

311 p. : il.

Using the system dynamics paradigm in teaching and learning technological university subjets

2nd International Conference on Education and New Learning Technologies

Analog VLSI-based, neuromorphic sensorimotor systems: modeling the primate oculomotor system

Using neuromorphic analog VLSI techniques for modeling large neural systems has several advantages over software techniques. By designing massively-parallel analog circuit arrays which are ubiquitous in neural systems, analog VLSI models are extremely fast, particularly when local interactions are important in the computation. While analog VLSI circuits are not as flexible as software methods, the constraints posed by this approach are often very similar to the constraints faced by biological systems. As a result, these constraints can offer many insights into the solutions found by evolution. This dissertation describes a hardware modeling effort to mimic the primate oculomotor system which requires both fast sensory processing and fast motor control. A one-dimensional hardware model of the primate eye has been built which simulates the physical dynamics of the biological system. It is driven by analog VLSI circuits mimicking brainstem and cortical circuits that control eye movements. In this framework, a visually-triggered saccadic system is demonstrated which generates averaging saccades. In addition, an auditory localization system, based on the neural circuits of the barn owl, is used to trigger saccades to acoustic targets in parallel with visual targets. Two different types of learning are also demonstrated on the saccadic system using floating-gate technology allowing the non-volatile storage of analog parameters directly on the chip. Finally, a model of visual attention is used to select and track moving targets against textured backgrounds, driving both saccadic and smooth pursuit eye movements to maintain the image of the target in the center of the field of view. This system represents one of the few efforts in this field to integrate both neuromorphic sensory processing and motor control in a closed-loop fashion.

Learning and using taxonomies for visual and olfactory classification

Humans are able of distinguishing more than 5000 visual categories even in complex environments using a variety of different visual systems all working in tandem. We seem to be capable of distinguishing thousands of different odors as well. In the machine learning community, many commonly used multi-class classifiers do not scale well to such large numbers of categories. This thesis demonstrates a method of automatically creating application-specific taxonomies to aid in scaling classification algorithms to more than 100 cate- gories using both visual and olfactory data. The visual data consists of images collected online and pollen slides scanned under a microscope. The olfactory data was acquired by constructing a small portable sniffing apparatus which draws air over 10 carbon black polymer composite sensors. We investigate performance when classifying 256 visual categories, 8 or more species of pollen and 130 olfactory categories sampled from common household items and a standardized scratch-and-sniff test. Taxonomies are employed in a divide-and-conquer classification framework which improves classification time while allowing the end user to trade performance for specificity as needed. Before classification can even take place, the pollen counter and electronic nose must filter out a high volume of background “clutter” to detect the categories of interest. In the case of pollen this is done with an efficient cascade of classifiers that rule out most non-pollen before invoking slower multi-class classifiers. In the case of the electronic nose, much of the extraneous noise encountered in outdoor environments can be filtered using a sniffing strategy which preferentially samples the visensor response at frequencies that are relatively immune to background contributions from ambient water vapor. This combination of efficient background rejection with scalable classification algorithms is tested in detail for three separate projects: 1) the Caltech-256 Image Dataset, 2) the Caltech Automated Pollen Identification and Counting System (CAPICS) and 3) a portable electronic nose specially constructed for outdoor use.

Distributed optimization in power networks and general multi-agent systems

The dissertation studies the general area of complex networked systems that consist of interconnected and active heterogeneous components and usually operate in uncertain environments and with incomplete information. Problems associated with those systems are typically large-scale and computationally intractable, yet they are also very well-structured and have features that can be exploited by appropriate modeling and computational methods. The goal of this thesis is to develop foundational theories and tools to exploit those structures that can lead to computationally-efficient and distributed solutions, and apply them to improve systems operations and architecture.

Specifically, the thesis focuses on two concrete areas. The first one is to design distributed rules to manage distributed energy resources in the power network. The power network is undergoing a fundamental transformation. The future smart grid, especially on the distribution system, will be a large-scale network of distributed energy resources (DERs), each introducing random and rapid fluctuations in power supply, demand, voltage and frequency. These DERs provide a tremendous opportunity for sustainability, efficiency, and power reliability. However, there are daunting technical challenges in managing these DERs and optimizing their operation. The focus of this dissertation is to develop scalable, distributed, and real-time control and optimization to achieve system-wide efficiency, reliability, and robustness for the future power grid. In particular, we will present how to explore the power network structure to design efficient and distributed market and algorithms for the energy management. We will also show how to connect the algorithms with physical dynamics and existing control mechanisms for real-time control in power networks.

The second focus is to develop distributed optimization rules for general multi-agent engineering systems. A central goal in multiagent systems is to design local control laws for the individual agents to ensure that the emergent global behavior is desirable with respect to the given system level objective. Ideally, a system designer seeks to satisfy this goal while conditioning each agent’s control on the least amount of information possible. Our work focused on achieving this goal using the framework of game theory. In particular, we derived a systematic methodology for designing local agent objective functions that guarantees (i) an equivalence between the resulting game-theoretic equilibria and the system level design objective and (ii) that the resulting game possesses an inherent structure that can be exploited for distributed learning, e.g., potential games. The control design can then be completed by applying any distributed learning algorithm that guarantees convergence to the game-theoretic equilibrium. One main advantage of this game theoretic approach is that it provides a hierarchical decomposition between the decomposition of the systemic objective (game design) and the specific local decision rules (distributed learning algorithms). This decomposition provides the system designer with tremendous flexibility to meet the design objectives and constraints inherent in a broad class of multiagent systems. Furthermore, in many settings the resulting controllers will be inherently robust to a host of uncertainties including asynchronous clock rates, delays in information, and component failures.