No description available.

The thesis analyzes how the expulsion of Germans from Czechoslovakia is treated, interpreted and staged. It concentrates on two questions: what strategies do the authors use to recover the memory of the events and how do the different communities translate and share their memories? In the first part I sketch the development of the political contexts and discourses of expulsion in German and Czech memory culture on the basis of the model of ‚floating gap' by Jan Assman. In the second part, I present seven ‚strategies of commemoration' (Documenting, Interpreting, Investigating, Exhibiting of fragmentarized Memories, Swearing/staging of Trauma, Drawing of Genealogies, Reading in Landscapes), which the authors use in Literature (and Art) to represent the expulsion. The third part focuses finally on the problem of intercultural translation of memories, its shareability and the inner dialogism. The constant line of the analysis is the irreductibility of connection of memory and forgetting, which underline each other from the level of text to the level of memory politic.

Layered learning is a machine learning paradigm used to develop autonomous robotic-based agents by decomposing a complex task into simpler subtasks and learns each sequentially. Although the paradigm continues to have success in multiple domains, performance can be unexpectedly unsatisfactory. Using Boolean-logic problems and autonomous agent navigation, we show poor performance is due to the learner forgetting how to perform earlier learned subtasks too quickly (favoring plasticity) or having difficulty learning new things (favoring stability). We demonstrate that this imbalance can hinder learning so that task performance is no better than that of a suboptimal learning technique, monolithic learning, which does not use decomposition. Through the resulting analyses, we have identified factors that can lead to imbalance and their negative effects, providing a deeper understanding of stability and plasticity in decomposition-based approaches, such as layered learning. To combat the negative effects of the imbalance, a complementary learning system is applied to layered learning. The new technique augments the original learning approach with dual storage region policies to preserve useful information from being removed from an agent’s policy prematurely. Through multi-agent experiments, a 28% task performance increase is obtained with the proposed augmentations over the original technique.

No description available.

No description available.

Cette thèse explore le développement de modèles d'apprentissage automatique robustes et compositionnels en exploitant les connaissances issues des goulots d'étranglement cognitifs qui structurent l'apprentissage humain et la représentation des connaissances. Notre recherche explore des concepts ancrés dans trois goulots d'étranglement cognitifs : l'apprentissage itéré, l'oubli et le réapprentissage, et l'attention sélective. Tout d'abord, nous examinons l'apprentissage itéré (IL), une théorie qui explique l'émergence de la compositionnalité dans les langues humaines. Traditionnellement étudiée dans des jeux référentiels simples imitant des expériences de sciences cognitives, nous étendons son application à un contexte plus large de question-réponse visuelle (VQA) en utilisant des réseaux de modules neuronaux (NMNs). En traitant la communication entre un générateur de programme et le moteur d'exécution dans un NMN comme une langue émergente, nous encourageons la compositionnalité dans sa structure, ce qui conduit à une généralisation systématique améliorée. Nos résultats démontrent que l'IL amplifie la compositionnalité là où une préférence pour celle-ci existe, améliorant ainsi la performance des tâches. Ensuite, nous investiguons le goulot d'étranglement cognitif de l'oubli et du réapprentissage, qui permet aux humains d'intégrer de nouvelles connaissances plus efficacement avec les connaissances existantes. L'oubli est souvent émulé dans l'apprentissage automatique par des réinitialisations partielles de paramètres. Cependant, nous proposons que la minimisation consciente de la netteté (SAM) incarne le paradigme de l'oubli et du réapprentissage, en effectuant un oubli ciblé des biais indésirables uniquement lors de la perturbation pour calculer les gradients de mise à jour. Notre perspective de l'oubli perturbé résout les contradictions dans le récit de la minimisation de la netteté et propose également une perturbation améliorée qui surpasse le SAM standard. Nous concluons que l'oubli ciblé sans compromettre l'état appris du modèle peut significativement améliorer la généralisation et la robustesse. Enfin, nous explorons l'attention sélective, un mécanisme cognitif qui permet aux humains de se concentrer sur les aspects saillants de leur environnement. La taille limitée de notre mémoire de travail impose la simplicité des concepts auxquels nous prêtons attention, et des représentations plus larges nécessitent de prêter attention séparément à différents sous-ensembles de nos stimuli. Cette capacité à construire des représentations complexes à partir de plus simples permet en partie la compréhension compositionnelle et la généralisation humaine. Nous appliquons ce concept pour proposer SPARO, un nouveau module de lecture qui structure les encodages dans CLIP et DINO en collections de concepts auxquels on prête attention séparément. Chaque concept SPARO est produit par une seule tête d'attention avec une dimensionnalité limitée, imitant le goulot d'étranglement de l'attention humaine. Nous démontrons que la structuration des encodages avec un a priori pour l'attention sélective améliore la compositionnalité, la généralisation en aval et la capacité d'intervention manuelle pour filtrer les concepts pertinents. / This thesis explores the development of robust and compositional machine learning models by harnessing insights from cognitive bottlenecks that structure human learning and knowledge representation. Our research explores concepts rooted in three cognitive bottlenecks: iterated learning, forgetting and relearning, and selective attention. First, we examine iterated learning (IL), a theory that explains the emergence of compositionality in human languages. Traditionally studied in simple referential games mimicking cognitive science experiments, we extend its application to a broader context of visual question-answering (VQA) using neural module networks (NMNs). By treating the communication between a program generator and the execution engine in an NMN as an emergent language, we encourage compositionality in its structure, leading to improved systematic generalization. Our findings demonstrate that IL amplifies compositionality where a preference for it exists, thereby enhancing task performance. Next, we investigate the cognitive bottleneck of forgetting and relearning, which enables humans to integrate new knowledge more effectively with existing knowledge. Forgetting is often emulated in machine learning through partial parameter resets. However, we propose that sharpness-aware minimization (SAM) embodies the forget-and-relearn paradigm, performing targeted forgetting of undesirable biases, only during perturbation to compute update gradients. Our perturbed forgetting perspective addresses contradictions in the sharpness minimization narrative and also offers an improved perturbation that outperforms standard SAM. We conclude that targeted forgetting without compromising the model's learned state can significantly enhance generalization and robustness. Finally, we explore selective attention, a cognitive mechanism that enables humans to focus on salient aspects of their environment. The limited size of our working memory forces the simplicity of the attended concepts, and broader representations require separately attending to different subsets of our stimuli. This ability to construct complex representations from simpler ones in part enables human compositional understanding and generalization. We apply this concept to propose SPARO, a new read-out module that structures encodings in CLIP and DINO as collections of separately attended concepts. Each SPARO concept is produced through a single attention head with limited dimensionality, emulating the human attention bottleneck. We demonstrate that structuring encodings with a prior for selective attention enhances compositionality, downstream generalization, and the capacity for manual intervention to filter relevant concepts.

Die vorliegende Dissertation untersucht Dissoziationen zwischen Vergessensverläufen für implizites und explizites Wissen. Aus diesem Ansatz können sich wesentliche Einschränkungen ergeben in Bezug auf die Annahme, sowohl impliziten als auch expliziten Prozessen liege ein einziges Gedächtnissystem oder ein einziger Mechanismus zugrunde. Im theoretischen Teil der Arbeit wird implizites Wissen als Information definiert, die ohne Intention gelernt und abgerufen wird, und die generelle Bedeutung einfacher Dissoziationen für Theorien impliziten Wissens erklärt. Ich gebe einen Überblick über die wesentlichen Forschungsprogramme in Hinblick auf Funktionen, Prozesse, Entwicklung, neuronale Korrelate und Vergessensverläufe impliziten Wissens und lege dar, daß der Vergleich der Vergessensverläufe impliziten und expliziten Wissens eine graduelle Perspektive ermöglicht, die die mit an einem einzelnen isolierten Zeitpunkt beobachteten einfachen Dissoziationen verbundenen Probleme überwindet, und auch dazu beitragen kann, die Lücke zwischen der Forschung zum impliziten Lernen und zum impliziten Gedächtnis zu schließen. In einer Reihe von vier Experimenten wurden studentische Versuchsteilnehmer Regelhaftigkeiten in der Umwelt ausgesetzt, die in eine künstliche Grammatikaufgabe (AG) oder Wahlreaktionsaufgabe (SRT) eingebettet waren. Für den Vergleich der Vergessensverläufe wurde das implizite (aus motorischen Reaktionszeiten erschlossene) und explizite (auf Wiedererkennung basierte) Wissen der Versuchspersonen jeweils vor und nach einem Behaltensintervall erfaßt. Die Befunde zeigen, daß sowohl in der AG als auch der SRT explizites Wissen schneller zerfällt als implizites. Darüber hinaus lieferte eine Interferenz-Aufgabe, die anstelle des Behaltensintervalls eingesetzt wurde, das gleiche Dissoziationsmuster. Schließlich wurde anhand einer Reihe von Simulationen geprüft, ob ein komputationales Ein-Speicher-Modell (Shanks, Wilkinson, & Channon, 2003) die experimentellen Befunde erklären kann. Die Simulationen zeigen, daß das Modell nur dann in Übereinstimmung mit den Daten gebracht werden kann, wenn zwischen den verschiedenen Meßzeitpunkten Veränderungen in den Parametern (a) der gemeinsamen Repräsentationsstärke für implizites und explizites Wissen, und (b) der Reliabilität des expliziten Maßes eingeführt werden. Meine Dissertation schlägt also (1) einen konzeptuellen Rahmen für explizites und implizites Wissen vor, erbringt (2) neue empirische Belege für Dissoziationen zwischen den Vergessensverläufen dieser Wissensformen, und identifiziert (3) die spezifischen Randbedingungen für ein Ein-Speicher- bzw. Ein-Prozess-Modell. / In this dissertation I investigate dissociations in the forgetting patterns of implicit and explicit knowledge. I claim that this approach may provide significant constraints for the assumption that a single system or mechanism determines both implicit and explicit processes. In the theoretical part, I construe a definition of implicit knowledge as information learned and retrieved without intention. I also explain the general role of single dissociations in theories of implicit knowledge. And I present an overview of the main lines of research concerned with the functions, operation, development, neural substrates, and forgetting patterns of implicit knowledge. In general, I argue that comparing the forgetting patterns of implicit and explicit knowledge may be best regarded from a graded perspective and may usefully bridge the gap between research on implicit learning and implicit memory. In a series of 4 Experiments university students were exposed to environmental regularities embedded in artificial grammar (AG) and serial reaction time (SRT) tasks. To compare the forgetting patterns, participants’ implicit (motor-performance based) and explicit (recognition based) knowledge was assessed before and after a retention interval. Taken together, the results indicate that explicit knowledge decays faster than implicit knowledge in both AG and SRT tasks. Furthermore, an interference task introduced instead of a retention interval produced the same pattern of dissociations. Finally, I conducted a set of simulations to asses the ability of a single-system model (Shanks, Wilkinson, & Channon, 2003) to account for my experimental results. The simulations showed that the model best fits the empirical data by introducing changes in the parameters related to (a) the common knowledge strength (for implicit and implicit knowledge), and (b) the reliability for the explicit test. In sum, my dissertation (1) suggests a conceptual framework for implicit and explicit knowledge, (2) provides new empirical evidence of dissociations in their forgetting patterns, and (3) identifies specific boundary conditions for a single-system model.

Accelerated long-term forgetting (ALF) is a recently described memory impairment associated with epilepsy. Patients with ALF appear to learn and initially retain new information normally, but forget it at an accelerated rate over subsequent days. ALF can have a profound impact on the lives of the people who suffer from it, but it is also of theoretical interest. In particular, the study of this disorder may provide insight into the mechanisms of memory consolidation. ALF is especially prevalent in transient epileptic amnesia (TEA), an epileptic syndrome in which the seizure focus is thought to be the medial temporal lobes (MTL). The MTL house the hippocampus and a number of other structures critical for declarative memory function. The aims of this doctoral thesis were to investigate which aspects of memory function are disrupted in patients with TEA-associated ALF, and to shed light on the neural basis of the memory impairment. Slow wave sleep (i.e. deep sleep) is known to exacerbate epileptic activity. It is also thought to play a key role in the consolidation of declarative memory. The most commonly posited explanation of ALF is the disruption of sleep- dependent memory consolidation. However, it remains possible that ALF is caused by a subtle problem with encoding that usually goes undetected until delayed memory tests. The results of this thesis demonstrate that sleep can actually benefit memory retention in TEA ALF patients just as much as it does in healthy people, and that it is not necessary for the retention interval to contain sleep in order for ALF to be seen. However, the relationship between slow wave sleep and memory was found to be abnormal in these patients. The amount of slow wave sleep, and the power in the slow oscillation frequency range, during the post-learning night correlated negatively with the benefit of that night of sleep for memory retention. Furthermore, resting-state brain activity patterns thought to reflect post-encoding memory reprocessing were found to correlate negatively with subsequent memory performance in these patients. Another chapter of this thesis provides evidence that TEA ALF patients encode memories abnormally; these patients showed reduced activity in the left hippocampus while viewing stimuli that they went on to forget. Furthermore, this encoding-related brain activity correlated with their long-term forgetting. The final experimental chapter reports a correlation in these patients between grey matter in the left hippocampus and long-term forgetting, which cannot entirely account for the encoding-related brain activity results. The hippocampus and its surrounding structures are thought to be critical to our ability to discriminate between similar stimuli and events. An intriguing hypothesis consistent with the pattern of results in this thesis is that ALF is caused by a functional impairment of the MTL that results in a diminished capacity to distinguish between similar experiences, ultimately causing memory problems; abnormally formed memories may interact with new material and memory consolidation processes in an aberrant manner, leading to retrieval deficits.

Based on Christina Reid&rsquo / s five Plays &ldquo / Tea in a China Cup,&rdquo / &ldquo / Did You Hear the One About the Irishman &hellip / ?,&rdquo / &ldquo / Joyriders,&rdquo / &ldquo / The Belle of the Belfast City,&rdquo / and &ldquo / My Name, Shall I Tell You My Name?&rdquo / the aim of this study is to put under discussion the idea that the sectarian conflict between the two ethno-religious communities in Northern Ireland is maintained deliberately and a national identity unique to the people in this country cannot be constructed at least in the near future. The Protestants in Northern Ireland cannot choose Irishness as a national identity because the Irishness has been monopolized by the Catholics, and cannot adopt the Britishness as a national identity because of the varieties in the social factors they have. Likewise, the Catholics in Northern Ireland do not call themselves British because their Catholicism involves an Irish identity with the rejection of the British rule, and they cannot truly entitle themselves Irish due to the differences in social conditions. However, both factions try to adhere themselves to a national identity through their communal ideology. The Protestants claim that they are part of Britain, while the Catholics claim that they are members of Irish Nation. This situation has led to reluctance in both communities to stop the conflictual circumstances which encourage both groups to tether to their traditions more intensely, to contribute to the otherization process reinforcing their social identity and lead them to impose their working ideology on their new members whose divergence from traditions will definitely pose a threat to their identity. Also, in this country the forgetting / remembering process, which is actually exploited to forge a national identity, is orchestrated by the two communities to enlarge the intercommunal chasm through the narration of the old stories and memories, creation of stories, commemoration activities and museumizing certain objects. Throughout the study the key points which will be highlighted are as follows: nation, national identity and nation building process, the sectarian conflict between the two communities in Northern Ireland, maintenance of conflictual situation and the employment of the forgetting / remembering process in Northern Ireland.

In visually guided control of a robot, a large residual problem occurs when the robot configuration is not in the neighborhood of the target acquisition configuration. Most existing uncalibrated visual servoing algorithms use quasi-Gauss-Newton methods which are effective for small residual problems. The solution used in this study switches between a full quasi-Newton method for large residual case and the quasi-Gauss-Newton methods for the small case. Visual servoing to handle large residual problems for tracking a moving target has not previously appeared in the literature. For large residual problems various Hessian approximations are introduced including an approximation of the entire Hessian matrix, the dynamic BFGS (DBFGS) algorithm, and two distinct approximations of the residual term, the modified BFGS (MBFGS) algorithm and the dynamic full Newton method with BFGS (DFN-BFGS) algorithm. Due to the fact that the quasi-Gauss-Newton method has the advantage of fast convergence, the quasi-Gauss-Newton step is used as the iteration is sufficiently near the desired solution. A switching algorithm combines a full quasi-Newton method and a quasi-Gauss-Newton method. Switching occurs if the image error norm is less than the switching criterion, which is heuristically selected. An adaptive forgetting factor called the dynamic adaptive forgetting factor (DAFF) is presented. The DAFF method is a heuristic scheme to determine the forgetting factor value based on the image error norm. Compared to other existing adaptive forgetting factor schemes, the DAFF method yields the best performance for both convergence time and the RMS error. Simulation results verify validity of the proposed switching algorithms with the DAFF method for large residual problems. The switching MBFGS algorithm with the DAFF method significantly improves tracking performance in the presence of noise. This work is the first successfully developed model independent, vision-guided control for large residual with capability to stably track a moving target with a robot.