Thesis (Ph. D.)--Duke University, 2008.

In typical restaurant recommendations, knowledge-based methods are used most often and do not take advantage of personal historical data. In this thesis, we are going to make some improvements to the Chicago Entrée restaurant recommender system. We will exploit the historical data and propose a weighted similarity approach to combine heuristic similarity with tag similarity between restaurants. Also, we show an improved way to mine the semantics of user behaviors using heuristic metric. These proposed approaches are evaluated by the comparison of three different pairwise approaches to learning to rank (LTR) in matrix factorization and five classic recommendation algorithms. The result shows that the combinatorial similarity outperforms the heuristic similarity on the precision, recall, F-score, and mean reciprocal rank.

In this thesis, behavior learning and generation models are proposed for simple and complex behaviors of robots using unsupervised learning methods. Simple behaviors are modeled by simple-behavior learning model (SBLM) and complex behaviors are modeled by complex-behavior learning model (CBLM) which uses previously learned simple or complex behaviors. Both models have common phases named behavior categorization, behavior modeling, and behavior generation. Sensory data are categorized using correlation based adaptive resonance theory network that generates motion primitives corresponding to robot&#039 / s base abilities in the categorization phase. In the modeling phase, Behavior-HMM, a modified version of hidden Markov model, is used to model the relationships among the motion primitives in a finite state stochastic network. In addition, a motion generator which is an artificial neural network is trained for each motion primitive to learn essential robot motor commands. In the generation phase, desired task is presented as a target observation and the model generates corresponding motion primitive sequence. Then, these motion primitives are executed successively by the motion generators which are specifically trained for the corresponding motion primitives. The models are not proposed for one specific behavior, but are intended to be bases for all behaviors. CBLM enhances learning capabilities by integrating previously learned behaviors hierarchically. Hence, new behaviors can take advantage of already discovered behaviors. The proposed models are tested on a robot simulator and the experiments showed that simple and complex-behavior learning models can generate requested behaviors effectively.

&ldquo / Developmental robotics&rdquo / proposes that, instead of trying to build a robot that shows intelligence once and for all, what one must do is to build robots that can develop. A robot should go through cognitive development just like an animal baby does. These robots should be equipped with behaviors that are simple but enough to bootstrap the system. Then, as the robot interacts with its environment, it should display increasingly complex behaviors. Studies in developmental psychology and neurophysiology provide support for the view that, the animals start with innate simple behaviors, and develop more complex behaviors through the differentiation, sequencing, and combination of these primitive behaviors. In this thesis, we propose such a development scheme for a mobile robot. J.J. Gibson&#039 / s concept of &ldquo / affordances&rdquo / provides the basis of this development scheme, and we use a formalization of affordances to make the robot learn about the dynamics of its interactions with its environment. We show that an autonomous robot can start with pre-coded primitive behaviors, and as it executes its behaviors randomly in an environment, it can learn the affordance relations between the environment and its behaviors. We then present two ways of using these learned structures, in achieving more complex, voluntary behaviors. In the first case, the robot still uses its pre-coded primitive behaviors only, but the sequencing of these are such that new more complex behaviors emerge. In the second case, the robot uses its pre-coded primitive behaviors to create new behaviors.

Building general purpose autonomous robots that suit a wide range of user-specified applications, requires a leap from today's task-specific machines to more flexible and general ones. To achieve this goal, one should move from traditional preprogrammed robots to learning robots that easily can acquire new skills. Learning from Demonstration (LfD) and Imitation Learning (IL), in which the robot learns by observing a human or robot tutor, are among the most popular learning techniques. Showing the robot how to perform a task is often more natural and intuitive than figuring out how to modify a complex control program. However, teaching robots new skills such that they can reproduce the acquired skills under any circumstances, on the right time and in an appropriate way, require good understanding of all challenges in the field. Studies of imitation learning in humans and animals show that several cognitive abilities are engaged to learn new skills correctly. The most remarkable ones are the ability to direct attention to important aspects of demonstrations, and adapting observed actions to the agents own body. Moreover, a clear understanding of the demonstrator's intentions and an ability to generalize to new situations are essential. Once learning is accomplished, various stimuli may trigger the cognitive system to execute new skills that have become part of the robot's repertoire. The goal of this thesis is to develop methods for learning from demonstration that mainly focus on understanding the tutor's intentions, and recognizing which elements of a demonstration need the robot's attention. An architecture containing required cognitive functions for learning and reproduction of high-level aspects of demonstrations is proposed. Several learning methods for directing the robot's attention and identifying relevant information are introduced. The architecture integrates motor actions with concepts, objects and environmental states to ensure correct reproduction of skills. Another major contribution of this thesis is methods to resolve ambiguities in demonstrations where the tutor's intentions are not clearly expressed and several demonstrations are required to infer intentions correctly. The provided solution is inspired by human memory models and priming mechanisms that give the robot clues that increase the probability of inferring intentions correctly. In addition to robot learning, the developed techniques are applied to a shared control system based on visual servoing guided behaviors and priming mechanisms. The architecture and learning methods are applied and evaluated in several real world scenarios that require clear understanding of intentions in the demonstrations. Finally, the developed learning methods are compared, and conditions where each of them has better applicability are discussed. / Att bygga autonoma robotar som passar ett stort antal olika användardefinierade applikationer kräver ett språng från dagens specialiserade maskiner till mer flexibla lösningar. För att nå detta mål, bör man övergå från traditionella förprogrammerade robotar till robotar som själva kan lära sig nya färdigheter. Learning from Demonstration (LfD) och Imitation Learning (IL), där roboten lär sig genom att observera en människa eller en annan robot, är bland de mest populära inlärningsteknikerna. Att visa roboten hur den ska utföra en uppgift är ofta mer naturligt och intuitivt än att modifiera ett komplicerat styrprogram. Men att lära robotar nya färdigheter så att de kan reproducera dem under nya yttre förhållanden, på rätt tid och på ett lämpligt sätt, kräver god förståelse för alla utmaningar inom området. Studier av LfD och IL hos människor och djur visar att flera kognitiva förmågor är inblandade för att lära sig nya färdigheter på rätt sätt. De mest anmärkningsvärda är förmågan att rikta uppmärksamheten på de relevanta aspekterna i en demonstration, och förmågan att anpassa observerade rörelser till robotens egen kropp. Dessutom är det viktigt att ha en klar förståelse av lärarens avsikter, och att ha förmågan att kunna generalisera dem till nya situationer. När en inlärningsfas är slutförd kan stimuli trigga det kognitiva systemet att utföra de nya färdigheter som blivit en del av robotens repertoar. Målet med denna avhandling är att utveckla metoder för LfD som huvudsakligen fokuserar på att förstå lärarens intentioner, och vilka delar av en demonstration som ska ha robotens uppmärksamhet. Den föreslagna arkitekturen innehåller de kognitiva funktioner som behövs för lärande och återgivning av högnivåaspekter av demonstrationer. Flera inlärningsmetoder för att rikta robotens uppmärksamhet och identifiera relevant information föreslås. Arkitekturen integrerar motorkommandon med begrepp, föremål och omgivningens tillstånd för att säkerställa korrekt återgivning av beteenden. Ett annat huvudresultat i denna avhandling rör metoder för att lösa tvetydigheter i demonstrationer, där lärarens intentioner inte är klart uttryckta och flera demonstrationer är nödvändiga för att kunna förutsäga intentioner på ett korrekt sätt. De utvecklade lösningarna är inspirerade av modeller av människors minne, och en primingmekanism används för att ge roboten ledtrådar som kan öka sannolikheten för att intentioner förutsägs på ett korrekt sätt. De utvecklade teknikerna har, i tillägg till robotinlärning, använts i ett halvautomatiskt system (shared control) baserat på visuellt guidade beteenden och primingmekanismer. Arkitekturen och inlärningsteknikerna tillämpas och utvärderas i flera verkliga scenarion som kräver en tydlig förståelse av mänskliga intentioner i demonstrationerna. Slutligen jämförs de utvecklade inlärningsmetoderna, och deras applicerbarhet under olika förhållanden diskuteras. / INTRO

Le stress prénatal est un sujet d'intérêt éthologique croissant en raison de ses effets sur la santé humaine et le bien-être des animaux. Cette thése de doctorat s’intéresse à la seiche Sepia officinalis, un modèle pratique dans lequel la progéniture en développement peut être séparée de leurs mères pour examiner diverses sources potentielles de stress en isolement expérimental. Plusieurs catégories de facteurs de stress ont été appliquées aux embryons et aux juvéniles et la progéniture résultante a été testée dans une série d'épreuves physiologiques et comportementales. L'objectif était de déterminer si différents types de stress prénatal affectent la seiche et, dans l'affirmative, comment ces effets se transmettent. Les données présentées démontrent que les stresseurs appliqués aux femelles reproductrices (stress maternel), ainsi que les stresseurs appliqués directement aux embryons (stress embryonnaire), affectent le comportement postnatal (y compris la structuration corporelle, la latéralisation cérébrale, la prédation et les schémas d'activité) la mémoire et / ou la neurobiologie (y compris les concentrations et le renouvellement de la monoamine, la taille des différents lobes cérébraux et la division cellulaire). Les résultats mettent en évidence la présence de trois voies par lesquelles le stress peut exercer des effets: sur le nombre de descendants produits par la femelle, la transmission de la femelle à sa progéniture et directement sur la progéniture elle-même. Les expériences ont également démontré qu'un facteur de stress complètement artificiel (lumière forte) affectait un éventail plus large de comportements chez la progéniture qu’un stress naturel (odeur de prédateur). Enfin, les données ont montré que l'environnement d'incubation et d’élevage peuvent également affecter la progéniture et méritent donc une attention particulière dans la formulation et l'interprétation des expériences avec cette espèce. Ces découvertes informent à la fois les pratiques de bien-être des seiches et d'autres céphalopodes (par exemple, réduisent la manipulation pour maximiser la reproduction) et élucident et renforcent les principes éthologiques qui s'appliquent au stress animal en général (par exemple la transmission des effets de stress de la mère à la progéniture). Compte tenu des informations fournies ici et dans de nombreuses autres études, la seiche et d'autres céphalopodes devraient continuer à servir de modèles comportementaux en éthologie et en biologie en général. / Prenatal stress is a subject of growing ethological interest due to its effects on human health and animal welfare. This Ph.D. thesis utilizes the cuttlefish Sepia officinalis, a convenient model in which developing offspring can be separated from their mothers to examine various potential sources of stress in experimental isolation. Several categories of stressors were applied to cuttlefish and cuttlefish eggs and the resulting offspring were tested in a range of physiological and behavioral tests. The goal was to determine if various types of prenatal stress affect cuttlefish, and if so, how these effects are transmitted. The data presented demonstrate that both stressors applied to reproducing females (maternal stress), as well as stressors applied directly to embryos (embryonic stress), affected post-natal behavior (including body patterning, brain lateralization, predation and activity patterns), learning, memory and/or neurobiology (including monoamine concentrations and turnover, the size of various brain lobes and cell division). The results highlight the presence of three pathways by which stress can exert effects: on the number of offspring produced by the female, transmission from the female to her offspring and directly on the offspring themselves. The experiments also demonstrated that a completely artificial stressor (bright light) affected a wider range of behaviors in offspring than a natural-occurring one (predator odor). Finally, the data showed that incubation and spawning environment can also affect offspring, and thus deserve attention in the formulation and interpretation of experiments with this species. These findings inform both welfare practices for cuttlefish and other cephalopods (e.g. reduce handling to maximize reproduction) as well as elucidating and reinforcing ethological principles that apply to animal stress in general (e.g. the transmission of stress effects from mother to offspring). Given the insight provided here and in numerous other studies, cuttlefish and other cephalopods should continue to serve as behavioral models in ethology and biology in general.