We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face'' and "non-face'' prototype clusters. At each image location, the local pattern is matched against the distribution-based model, and a trained classifier determines, based on the local difference measurements, whether or not a human face exists at the current image location. We provide an analysis that helps identify the critical components of our system.

The work presented in this dissertation investigates techniques for robot Learning from Demonstration (LFD). LFD is a well established approach where the robot is to learn from a set of demonstrations. The dissertation focuses on LFD where a human teacher demonstrates a behavior by controlling the robot via teleoperation. After demonstration, the robot should be able to reproduce the demonstrated behavior under varying conditions. In particular, the dissertation investigates techniques where previous behavioral knowledge is used as bias for generalization of demonstrations. The primary contribution of this work is the development and evaluation of a semi-reactive approach to LFD called Predictive Sequence Learning (PSL). PSL has many interesting properties applied as a learning algorithm for robots. Few assumptions are introduced and little task-specific configuration is needed. PSL can be seen as a variable-order Markov model that progressively builds up the ability to predict or simulate future sensory-motor events, given a history of past events. The knowledge base generated during learning can be used to control the robot, such that the demonstrated behavior is reproduced. The same knowledge base can also be used to recognize an on-going behavior by comparing predicted sensor states with actual observations. Behavior recognition is an important part of LFD, both as a way to communicate with the human user and as a technique that allows the robot to use previous knowledge as parts of new, more complex, controllers. In addition to the work on PSL, this dissertation provides a broad discussion on representation, recognition, and learning of robot behavior. LFD-related concepts such as demonstration, repetition, goal, and behavior are defined and analyzed, with focus on how bias is introduced by the use of behavior primitives. This analysis results in a formalism where LFD is described as transitions between information spaces. Assuming that the behavior recognition problem is partly solved, ways to deal with remaining ambiguities in the interpretation of a demonstration are proposed. The evaluation of PSL shows that the algorithm can efficiently learn and reproduce simple behaviors. The algorithm is able to generalize to previously unseen situations while maintaining the reactive properties of the system. As the complexity of the demonstrated behavior increases, knowledge of one part of the behavior sometimes interferes with knowledge of another parts. As a result, different situations with similar sensory-motor interactions are sometimes confused and the robot fails to reproduce the behavior. One way to handle these issues is to introduce a context layer that can support PSL by providing bias for predictions. Parts of the knowledge base that appear to fit the present context are highlighted, while other parts are inhibited. Which context should be active is continually re-evaluated using behavior recognition. This technique takes inspiration from several neurocomputational models that describe parts of the human brain as a hierarchical prediction system. With behavior recognition active, continually selecting the most suitable context for the present situation, the problem of knowledge interference is significantly reduced and the robot can successfully reproduce also more complex behaviors.

Intelligent Tutoring Systems (ITS) have a significant educational impact on student's learning. However, researchers report time intensive interaction is needed between ITS developers and domain-experts to gather and represent domain knowledge. The challenge is augmented when the target domain is ill-defined. The primary problem resides in often using traditional approaches for gathering domain and tutoring experts' knowledge at design time and conventional methods for knowledge representation built for well-defined domains. Similar to evolving knowledge acquisition approaches used in other fields, we replace this restricted view of ITS knowledge learning merely at design time with an incremental approach that continues training the ITS during run time. We investigate a gradual knowledge learning approach through continuous instructor-student demonstrations. We present a Mixed-response Intelligent Tutoring System based on Learning from Demonstration that gathers and represents knowledge at run time. Furthermore, we implement two knowledge representation methods (Weighted Markov Models and Weighted Context Free Grammars) and corresponding algorithms for building domain and tutoring knowledge-bases at run time. We use students' solutions to cybersecurity exercises as the primary data source for our initial framework testing. Five experiments were conducted using various granularity levels for data representation, multiple datasets differing in content and size, and multiple experts to evaluate framework performance. Using our WCFG-based knowledge representation method in conjunction with a finer data representation granularity level, the implemented framework reached 97% effectiveness in providing correct feedback. The ITS demonstrated consistency when applied to multiple datasets and experts. Furthermore, on average, only 1.4 hours were needed by instructors to build the knowledge-base and required tutorial actions per exercise. Finally, the ITS framework showed suitable and consistent performance when applied to a second domain. These results imply that ITS domain models for ill-defined domains can be gradually constructed, yet generate successful results with minimal effort from instructors and framework developers. We demonstrate that, in addition to providing an effective tutoring performance, an ITS framework can offer: scalability in data magnitude, efficiency in reducing human effort required for building a confident knowledge-base, metacognition in inferring its current knowledge, robustness in handling different pedagogical and tutoring criteria, and portability for multiple domain use.

Experience feedback from accidents is important for preventive work in companies, authorities and other organisations. This thesis focused on experience feedback from accidents that take place in everyday life, in our neighbourhoods, in our workplaces, in our schools, in traffic and transportation. Essay I is an overview of the literature on learning from accidents and incidents. The focus in this essay is on literature that evaluates the effectiveness and usefulness of different methods in accident investigations. Conclusions drawn from this literature review are that the dissemination of results and knowledge from accident investigations must be improved, and experience feedback systems should be integrated into overall systems of risk management. Essay II is based on an evaluation of the investigation board for workplace accidents (HAKO) that was carried out on commission of the Swedish Work Environment Authority. It was concluded that the accident reports published by HAKO had a high qualitative level but the dissemination of results from the investigations was weak. Essay III investigates twenty-eight supervision cases from eleven Swedish local Environment and Health Administrations. The overall goal of the study was to find out how, and to what extent, experience feedback occurs in Swedish municipalities. Two major problems relevant for the experience feedback have been found; namely that the inspectors do not have enough guidance on how to interpret the law and that they would like more information on what happens to legal cases that they have handed over to the public prosecutors and the police. Essay IV is a document study of incident reports from two municipal fire and rescue services. The overall purpose of this study was to investigate if information from the rescue services could be used to improve experience feedback in sectors where it is weak or non-existent. In the 1120 incident reports that were studied, we found 217 proposals for improvement but these proposals were not used for experience feedback. It is concluded that the reports contain valuable information but this information is not used to prevent future accidents. Essay V investigates experience feedback in Swedish authorities working with accident prevention. The essay is based on two interview studies. In the first study, 21 Swedish authorities participated, and several of these authorities seem to have a functioning experience feedback despite the lack of systematic routines and methods. Yet, only four of the 21 authorities actually handle the whole experience feedback process. These four have at least one common denominator; they have an experience feedback that is turning more inwards than outwards. The second study was a follow-up study of some of the results from the first study, concerning the dissemination of results from experience feedback. / QC 20101209

There is a lot of research conducted in the field of general entrepreneurship, entrepreneurial learning, and entrepreneurial innovation. However, as Jason Cope (2003) came across during his research, there is little to none research made within the field of entrepreneurial learning from failure, especially from bankruptcy. The purpose of this thesis is to explore if it is possible forentrepreneurs to obtain “higher-level learning” from a bankruptcy. The research concerns whether or not entrepreneurs can learn from their mistakes, and in turn use this learning in order to become more successful entrepreneur in future undertakings. The thesis contributes to a research project on entrepreneurial response to firm failure, initiated by Anna Jenkins (2008). As stated above, there is little to none research conducted in the field of entrepreneurial learning from a bankruptcy. Therefore theories considered closely and partly related to the subject have been revised. The overarching theory, the “Experiential learning theory” (Kolb, 1984) describes how experience can be transformed into genuine knowledge, through the steps: experiencing an event, reflecting on the event, understanding the principle under which the particular event falls and testing this new understanding under different circumstances. Jason Cope (2003) has found that entrepreneurs can obtain higher-level learning from experiencing discontinuous criticalevents by going through the phases; facing, overcoming and reflecting on events that occur during the running of a firm. This learning can be transformational; the entrepreneur realizes that current methods are insufficient, forcing him or her to adapt and change methods in future undertakings. The main objective in this thesis was not to draw any final conclusions, rather to explore newvaluable information that can be interpreted in the main project as well as in future projects. To gather information we used a qualitative method, in which we interviewed five entrepreneurs who had recently experienced a bankruptcy. The empirical findings were later analyzed in thelight of the frame of references and the authors own viewpoint, by conducting a within case/cross case comparison. The results show that two out of five entrepreneurs had transformed the experience from their bankruptcy into new genuine knowledge, thereby confirming that it is possible to obtain higherlevel learning from a bankruptcy. They realized their own mistakes and changed their methods in order to avoid making the same mistakes again. Three of the respondents had not critically reflected on their bankruptcy, thereby gained no new knowledge of how to change their methods in future undertakings. The major reasons as to why they were unable to do so were that they blamed external factors as the reason for bankruptcy. One of the interviewees was emotionally blocked during the bankruptcy and therefore unable to contemplate what had went wrong. / Det finns mycket forskning inom området entreprenörskap, entreprenöriel inlärning, och entreprenöriel innovation. Däremot finns det, vilket Jason Cope (2003) har upptäckt, lite eller ingen existerande forskning inom området entreprenöriel inlärning från ett misslyckande, som till exempel en konkurs. Syftet med den här uppsatsen är att utforska om det är möjligt för entreprenörer att uppnå ”higher-level learning” från en konkurs. Vi ämnar undersöka om entreprenörer kan lära sig av sina misstag och sedan använda dessa lärdomar i framtida projekt i sin strävan mot att bli bättre entreprenörer. Uppsatsen är tänkt som ett bidrag till ett forskningsprojekt om entreprenörers reaktion på företagsmisslyckande, bedriven av Anna Jenkins(2008). Som nämnt ovan finns det knappt någon existerande forskning angående entreprenöriel inlärning från en konkurs, vilket har lett till att de teorier som är relaterade till ämnet har blivit reviderade. Den övergripande teorin, ”The Experiental Learning Theory” (Kolb, 1984) beskriver hur erfarenhet kan bli omvandlad till kunskap genom att följa stegen: aktivt uppleva en händelse,reflektera över händelsen, kunna förstå och analysera händelsen, och slutligen använda sin nya kunskap vid ett senare tillfälle. Jason Cope (2003) har upptäckt att entreprenörer kan nå en ”higher-level learning” genom att uppleva diskontinuerliga kritiska händelser och gå igenom dessafaser: tillmötesgå, övervinna/bemästra och reflektera över händelser som inträffar under företagandets gång. Den här inlärningen kan sedan omvandlas; entreprenören inser att hans nuvarande företagarmetoder inte är optimala, vilket leder honom/henne till att anpassa sig till situationen och ändra sina metoder i framtida projekt. Målsättningen med den här uppsatsen var inte att dra några avgörande slutsatser, utan istället att utforska och behandla ny, värdefull information som kan bli användbar i den avhandling vi önskar bidra till, samt för andra framtida forskningsprojekt. För att samla information använde vi oss av kvalitativa intervjuer. Vi intervjuade fem entreprenörer, vilka alla nyligen hade upplevt en konkurs. Empirin analyserades sedan med hjälp av våra utvalda teorier och våra egna synpunkter, genom att göra en ”cross case comparison”. Vårt resultat visar att två av fem entreprenörer har omvandlat sina upplevelser kring konkursen till genuin kunskap och därmed bekräftat att det är möjligt att uppnå ”higher-level learning” av en konkurs. De har insett sina egna misstag och ändrat sina metoder för att förhindra att samma misstag upprepas. Tre av respondenterna har inte reflekterat kritiskt över konkursen, och därför inte fått någon ny kunskap angående hur de skulle kunna ändra sina metoder inom företagande inför framtida projekt. Den främsta anledningen till varför de var oförmögna att reflektera över händelsen var att de skyllde konkursen främst på externa faktorer. En av de intervjuade var även känslomässigt blockerad under konkursen och därför inkapabel att begrunda sina misstag.

The example based processing problem can be expressed as: "Given an example of an image or video before and after processing, apply a similar processing to a new image or video". Our thesis is that there are some problems where a single general algorithm can be used to create varieties of outputs, solely by presenting examples of what is desired to the algorithm. This is valuable if the algorithm to produce the output is non-obvious, e.g. an algorithm to emulate an example painting's style. We limit our investigations to example based processing of images, video, and 3D models as these data types are easy to acquire and experiment with. We represent this problem first as a texture synthesis influenced sampling problem, where the idea is to form feature vectors representative of the data and then sample them coherently to synthesize a plausible output for the new image or video. Grounding the problem in this manner is useful as both problems involve learning the structure of training data under some assumptions to sample it properly. We then reduce the problem to a labeling problem to perform example based processing in a more generalized and principled manner than earlier techniques. This allows us to perform a different estimation of what the output should be by approximating the optimal (and possibly not known) solution through a different approach.

This thesis investigates how a robot can use action generation mechanisms to recognize the action of an observed actor in an on-line manner i.e., before the completion of the action. Towards this end, Dynamic Movement Primitives (DMP), an action generation method proposed for imitation, are modified to recognize the actions of an actor. Specifically, a human actor performed three different reaching actions to two different objects. Three DMP&#039 / s, each corresponding to a different reaching action, were trained using this data. The proposed method used an object-centered coordinate system to define the variables for the action, eliminating the difference between the actor and the robot. During testing, the robot simulated action trajectories by its learned DMPs and compared the resulting trajectories against the observed one. The error between the simulated and the observed trajectories were integrated into a recognition signal, over which recognition was done. The proposed method was applied on the iCub humanoid robot platform using an active motion capture device for sensing. The results showed that the system was able to recognize actions with high accuracy as they unfold in time. Moreover, the feasibility of the approach is demonstrated in an interactive game between the robot and a human.

The vision of personal robot assistants continues to become more realistic with technological advances in robotics. The increase in the capabilities of robots, presents boundless opportunities for them to perform useful tasks for humans. However, it is not feasible for engineers to program robots for all possible uses. Instead, we envision general-purpose robots that can be programmed by their end-users. Learning from Demonstration (LfD), is an approach that allows users to program new capabilities on a robot by demonstrating what is required from the robot. Although LfD has become an established area of Robotics, many challenges remain in making it effective and intuitive for naive users. This thesis contributes to addressing these challenges in several ways. First, the problems that occur in teaching-learning interactions between humans and robots are characterized through human-subject experiments in three different domains. To address these problems, two mechanisms for guiding human teachers in their interactions are developed: embodied queries and teaching heuristics. Embodied queries, inspired from Active Learning queries, are questions asked by the robot so as to steer the teacher towards providing more informative demonstrations. They leverage the robot's embodiment to physically manipulate the environment and to communicate the question. Two technical contributions are made in developing embodied queries. The first is Active Keyframe-based LfD -- a framework for learning human-segmented skills in continuous action spaces and producing four different types of embodied queries to improve learned skills. The second is Intermittently-Active Learning in which a learner makes queries selectively, so as to create balanced interactions with the benefits of fully-active learning. Empirical findings from five experiments with human subjects are presented. These identify interaction-related issues in generating embodied queries, characterize human question asking, and evaluate implementations of Intermittently-Active Learning and Active Keyframe-based LfD on the humanoid robot Simon. The second mechanism, teaching heuristics, is a set of instructions given to human teachers in order to elicit more informative demonstrations from them. Such instructions are devised based on an understanding of what constitutes an optimal teacher for a given learner, with techniques grounded in Algorithmic Teaching. The utility of teaching heuristics is empirically demonstrated through six human-subject experiments, that involve teaching different concepts or tasks to a virtual agent, or teaching skills to Simon. With a diverse set of human subject experiments, this thesis demonstrates the necessity for guiding humans in teaching interactions with robots, and verifies the utility of two proposed mechanisms in improving sample efficiency and final performance, while enhancing the user interaction.

<p>There is a lot of research conducted in the field of general entrepreneurship, entrepreneurial learning, and entrepreneurial innovation. However, as Jason Cope (2003) came across during his research, there is little to none research made within the field of entrepreneurial learning from failure, especially from bankruptcy. The purpose of this thesis is to explore if it is possible forentrepreneurs to obtain “higher-level learning” from a bankruptcy. The research concerns whether or not entrepreneurs can learn from their mistakes, and in turn use this learning in order to become more successful entrepreneur in future undertakings. The thesis contributes to a research project on entrepreneurial response to firm failure, initiated by Anna Jenkins (2008).</p><p>As stated above, there is little to none research conducted in the field of entrepreneurial learning from a bankruptcy. Therefore theories considered closely and partly related to the subject have been revised. The overarching theory, the “Experiential learning theory” (Kolb, 1984) describes how experience can be transformed into genuine knowledge, through the steps: experiencing an event, reflecting on the event, understanding the principle under which the particular event falls and testing this new understanding under different circumstances. Jason Cope (2003) has found that entrepreneurs can obtain higher-level learning from experiencing discontinuous criticalevents by going through the phases; facing, overcoming and reflecting on events that occur during the running of a firm. This learning can be transformational; the entrepreneur realizes that current methods are insufficient, forcing him or her to adapt and change methods in future undertakings.</p><p>The main objective in this thesis was not to draw any final conclusions, rather to explore newvaluable information that can be interpreted in the main project as well as in future projects. To gather information we used a qualitative method, in which we interviewed five entrepreneurs who had recently experienced a bankruptcy. The empirical findings were later analyzed in thelight of the frame of references and the authors own viewpoint, by conducting a within case/cross case comparison.</p><p>The results show that two out of five entrepreneurs had transformed the experience from their bankruptcy into new genuine knowledge, thereby confirming that it is possible to obtain higherlevel learning from a bankruptcy. They realized their own mistakes and changed their methods in order to avoid making the same mistakes again. Three of the respondents had not critically reflected on their bankruptcy, thereby gained no new knowledge of how to change their methods in future undertakings. The major reasons as to why they were unable to do so were that they blamed external factors as the reason for bankruptcy. One of the interviewees was emotionally blocked during the bankruptcy and therefore unable to contemplate what had went wrong.</p> / <p>Det finns mycket forskning inom området entreprenörskap, entreprenöriel inlärning, och entreprenöriel innovation. Däremot finns det, vilket Jason Cope (2003) har upptäckt, lite eller ingen existerande forskning inom området entreprenöriel inlärning från ett misslyckande, som till exempel en konkurs. Syftet med den här uppsatsen är att utforska om det är möjligt för entreprenörer att uppnå ”higher-level learning” från en konkurs. Vi ämnar undersöka om entreprenörer kan lära sig av sina misstag och sedan använda dessa lärdomar i framtida projekt i sin strävan mot att bli bättre entreprenörer. Uppsatsen är tänkt som ett bidrag till ett forskningsprojekt om entreprenörers reaktion på företagsmisslyckande, bedriven av Anna Jenkins(2008).</p><p>Som nämnt ovan finns det knappt någon existerande forskning angående entreprenöriel inlärning från en konkurs, vilket har lett till att de teorier som är relaterade till ämnet har blivit reviderade. Den övergripande teorin, ”The Experiental Learning Theory” (Kolb, 1984) beskriver hur erfarenhet kan bli omvandlad till kunskap genom att följa stegen: aktivt uppleva en händelse,reflektera över händelsen, kunna förstå och analysera händelsen, och slutligen använda sin nya kunskap vid ett senare tillfälle. Jason Cope (2003) har upptäckt att entreprenörer kan nå en ”higher-level learning” genom att uppleva diskontinuerliga kritiska händelser och gå igenom dessafaser: tillmötesgå, övervinna/bemästra och reflektera över händelser som inträffar under företagandets gång. Den här inlärningen kan sedan omvandlas; entreprenören inser att hans nuvarande företagarmetoder inte är optimala, vilket leder honom/henne till att anpassa sig till situationen och ändra sina metoder i framtida projekt.</p><p>Målsättningen med den här uppsatsen var inte att dra några avgörande slutsatser, utan istället att utforska och behandla ny, värdefull information som kan bli användbar i den avhandling vi önskar bidra till, samt för andra framtida forskningsprojekt. För att samla information använde vi oss av kvalitativa intervjuer. Vi intervjuade fem entreprenörer, vilka alla nyligen hade upplevt en konkurs. Empirin analyserades sedan med hjälp av våra utvalda teorier och våra egna synpunkter, genom att göra en ”cross case comparison”.</p><p>Vårt resultat visar att två av fem entreprenörer har omvandlat sina upplevelser kring konkursen till genuin kunskap och därmed bekräftat att det är möjligt att uppnå ”higher-level learning” av en konkurs. De har insett sina egna misstag och ändrat sina metoder för att förhindra att samma misstag upprepas. Tre av respondenterna har inte reflekterat kritiskt över konkursen, och därför inte fått någon ny kunskap angående hur de skulle kunna ändra sina metoder inom företagande inför framtida projekt. Den främsta anledningen till varför de var oförmögna att reflektera över händelsen var att de skyllde konkursen främst på externa faktorer. En av de intervjuade var även känslomässigt blockerad under konkursen och därför inkapabel att begrunda sina misstag.</p><p> </p>

Communicating with natural language interfaces is a long-standing, ultimate goal for artificial intelligence (AI) agents to pursue, eventually. One core issue toward this goal is "grounded" language learning, a process of learning the semantics of natural language with respect to relevant perceptual inputs. In order to ground the meanings of language in a real world situation, computational systems are trained with data in the form of natural language sentences paired with relevant but ambiguous perceptual contexts. With such ambiguous supervision, it is required to resolve the ambiguity between a natural language (NL) sentence and a corresponding set of possible logical meaning representations (MR). In this thesis, we focus on devising effective models for simultaneously disambiguating such supervision and learning the underlying semantics of language to map NL sentences into proper logical MRs. We present probabilistic generative models for learning such correspondences along with a reranking model to improve the performance further. First, we present a probabilistic generative model that learns the mappings from NL sentences into logical forms where the true meaning of each NL sentence is one of a handful of candidate logical MRs. It simultaneously disambiguates the meaning of each sentence in the training data and learns to probabilistically map an NL sentence to its corresponding MR form depicted in a single tree structure. We perform evaluations on the RoboCup sportscasting corpus, proving that our model is more effective than those proposed by previous researchers. Next, we describe two PCFG induction models for grounded language learning that extend the previous grounded language learning model of Börschinger, Jones, and Johnson (2011). Börschinger et al.’s approach works well in situations of limited ambiguity, such as in the sportscasting task. However, it does not scale well to highly ambiguous situations when there are large sets of potential meaning possibilities for each sentence, such as in the navigation instruction following task first studied by Chen and Mooney (2011). The two models we present overcome such limitations by employing a learned semantic lexicon as a basic correspondence unit between NL and MR for PCFG rule generation. Finally, we present a method of adapting discriminative reranking to grounded language learning in order to improve the performance of our proposed generative models. Although such generative models are easy to implement and are intuitive, it is not always the case that generative models perform best, since they are maximizing the joint probability of data and model, rather than directly maximizing conditional probability. Because we do not have gold-standard references for training a secondary conditional reranker, we incorporate weak supervision of evaluations against the perceptual world during the process of improving model performance. All these approaches are evaluated on the two publicly available domains that have been actively used in many other grounded language learning studies. Our methods demonstrate consistently improved performance over those of previous studies in the domains with different languages; this proves that our methods are language-independent and can be generally applied to other grounded learning problems as well. Further possible applications of the presented approaches include summarized machine translation tasks and learning from real perception data assisted by computer vision and robotics. / text