Un des thèmes de recherche privilégié pour les sciences cognitives et l'intelligence artificielle est l'étude des capacités d'association du cerveau humain. L'objectif est de développer des modèles de mémoires dotés de caractéristiques similaires, que ce soit en termes d'adaptabilité, d'efficacité, ou de robustesse. Plusieurs modèles de mémoires associatives ont été développés et présentés dans la littérature, parmi eux le modèle de mémoire associative bidirectionnelle BAM de Kosko (Kosko, 1988). Ce modèle utilise une règle d'apprentissage hebbienne qui le rend plausible biologiquement, mais il possède plusieurs limitations cependant. En effet, sa règle d'apprentissage impose des contraintes d'orthogonalité entre les différents motifs appris qui entraine une faible capacité de mémorisation et une faible résilience face au bruit. De plus, le modèle peut apprendre uniquement des patrons encodés en binaire et linéairement séparables. De nombreux efforts ont été, et continuent aujourd'hui à être déployés pour tenter d'améliorer le modèle de Kosko. La plupart visent l'augmentation de la capacité de stockage et l'amélioration de la performance de rappel. Quelques-uns des modèles proposés réussissent à classifier des problèmes non séparables linéairement, mais s'éloignent de l'architecture originale de Kosko ou parfois, utilisent des méthodes d'apprentissage qui s'écartent du principe de Hebb, ce qui les rend moins plausibles biologiquement. Dans le présent mémoire, nous approfondissons l'étude d'un modèle récent de BAM, proposé par Chartier et Boukadoum (2006a) et caractérisé par une fonction de sortie chaotique, une architecture asymétrique, et une règle d'apprentissage hebbienne modifiée. Plus spécifiquement, nous étudions l'impact de modifier la fonction de sortie, en lui ajoutant un paramètre d'asymétrie, sur la capacité du réseau à traiter des tâches de classification non linéairement séparables. Nous nous inspirons de la théorie des catastrophes pour le cadre théorique de notre étude. Nous expérimentons sur le modèle en vue d'améliorer sa performance de classification sans complexifier son architecture ou nous écarter de la plausibilité biologique de la règle d'apprentissage. Pour ce faire, nous utilisons et comparons plusieurs algorithmes de recherche heuristiques, dont certains inspirés de l'évolution naturelle, afin de concevoir des modèles de classification puissants, potentiellement capables de reproduire l'efficacité des processus cognitifs naturels. Les principes exposés dans ce mémoire, se sont montrés efficaces pour le modèle BAM et peuvent faire l'objet de recherches intéressantes, notamment pour l'amélioration du potentiel des modèles connexionnistes récurrents. ______________________________________________________________________________ MOTS-CLÉS DE L’AUTEUR : mémoire associative bidirectionnelle, réseaux de neurones artificiels, classification, dynamique chaotique, catastrophe fronce.

With the rapid growth of load demand, the distribution system is becoming more and more complicated, and the operational efficiency and service quality deteriorated. Power system protection is important for service reliability and quality assurance. Various faults may occur due to natural and artificial calamity. To reduce the outage duration and promptly restore power services, fault section estimate has to be done effectively with appeared fault alarms. The distribution system containing numerous protective facilities and switch equipment ranges over wide boundary. It becomes very complicated for dispatchers to obtain restoration plan for out-of-service areas. To cope with the problem, an effective tool is helpful for the restoration. This thesis proposes the use of Bi-directional associative memory networks (BAMN) to develop alarm processing. And use of Probabilistic Neural Network (PNN) to develop fault section detection, fault isolation, and restoration system. A distribution system is selected for computer simulation to demonstrate the effectiveness of the proposed system. The thesis proposes to use Bi-directional Associative Memory Network¡]BAMN¡^ to pre-process the signal gained from SCADA Interface, and transmit correct signal to Probabilistic Neural Network (PNN) for restoration plan . Computer simulation shows a simplified model to shorten the processing time in this study.

The new approach for sensor diagnostics is presented. The approach, Enhanced Autoassociative Neural Networks (E-AANN), adds enhancement to Autoassociative Neural Networks (AANN) developed by Kramer in 1992. This enhancement allows AANN to identify faulty sensors. E-AANN uses a secondary optimization process to identify and reconstruct sensor faults. Two common types of sensor faults are investigated, drift error and shift or offset error. In the case of drift error, the sensor error occurs gradually while in the case of shift error, the sensor error occurs abruptly. EAANN catches these error types. A chiller model provided synthetic data to test the diagnostic approach under various noise level conditions. The results show that sensor faults can be detected and corrected in noisy situations with the E-AANN method described. In high noisy situations (10% to 20% noise level), E-AANN performance degrades. E-AANN performance in simple dynamic systems was also investigated. The results show that in simple dynamic situations, E-AANN identifies faulty sensors.

We investigated the concurrent effects of arousal and encoding specificity as related to background music on associative memory accuracy. Extant literature suggested these factors affect memory, but their combined effect in musical stimuli was not clear and may affect memory differentially for young and older adults. Specifically, we sought to determine if music can be used as a mnemonic device to overcome the associative memory deficits typically experienced by healthy older adults. We used a paired-associates memory task in which young and older adults listened to either highly or lowly arousing music or to silence while simultaneously studying same gender face-name pairs. Participants' memory was then tested for these pairs while listening to either the same or different music selections. We found that young adults' memory performance was not affected by any of the music listening conditions. Music listening, however, was detrimental for older adults. Specifically, their memory performance was worse for all music conditions, particularly if the music was highly arousing. Young adults' pattern of results was not reflected in their subjective ratings of helpfulness; they felt that all music was helpful to their performance yet there was no indication of this in the results. Older adults were more aware of the detriment of music on their performance, rating some highly arousing music as less helpful than silence. We discuss possible reasons for this pattern and conclude that these results are most consistent with the theory that older adults' failure to inhibit processing of distracting task-irrelevant information, in this case background music, contributes to their elevated memory failures.

Thesis (Ph. D.)--University of Missouri-Columbia, 2000. / Typescript. Vita. Includes bibliographical references (leaves 104-106). Also available on the Internet.

Thesis (Ph. D.)--University of Missouri-Columbia, 2000. / Typescript. Vita. Includes bibliographical references (leaves 104-106). Also available on the Internet.

The paper examines the application of the concept of economic efficiency to organizational issues of collective information processing in decision making. Information processing is modeled in the framework of the dynamic parallel-processing model of associative computation with an endogenous set-up cost of the processors. The model is extended to include the specific features of collective information processing in the team of decision makers which could cause an error in data analysis. In such a model, the conditions for efficient organization of information processing are defined and the architecture of the efficient structures is considered. We show that specific features of collective decision making procedures require a broader framework for judging organizational efficiency than has traditionally been adopted. In particular, and contrary to the results presented in economic literature, we show that in human data processing (unlike in computer systems), there is no unique architecture for efficient information processing structures, but a number of various efficient forms can be observed. The results indicate that technological progress resulting in faster data processing (ceteris paribus) will lead to more regular information processing structures. However, if the relative cost of the delay in data analysis increases significantly, less regular structures could be efficient. (authors' abstract) / Series: Discussion Papers of the Institute for Economic Geography and GIScience

Research has shown that detecting and judging causal relationships requires associative learning and memory. Retrospective revaluation of causal cues requires associative memory (Aitken, Larkin, & Dickinson, 2001) to bind multiple cues together and use these associations to retrieve unseen cues for revaluation of their associative value. The difficulty that older adults experience with respect to retrospective revaluation could occur because of their deficit in associative binding and retrieval (Mutter, Atchley, & Plumlee, 2012). Like retrospective revaluation, blocking requires cue – outcome associative learning, but unlike retrospective revaluation, blocking does not require binding two cues together nor does it require using the resulting association between these cues for retrieval. Older adults display no deficit in blocking (Hannah, Allan, & Young, 2012; Holder & Mutter, in submission). To assess the effects of aging on associative learning and memory in causal judgment, this study examined age effects in retrospective revaluation and blocking using an allergy scenario in a streamed-trial task (Hannah, Crump, Allan, & Siegel, 2009; Hannah et al., 2012). This study found that older and younger adults both displayed blocking effects, which supports past research. Additionally, it was found that older and younger adults displayed retrospective revaluation in working memory. The ability for older adults to display retrospective revaluation in working memory is a new finding. It suggests that there may be a decrement in associative long-term memory, but associative processes in working memory may be intact.

In this thesis, we build upon the work of Plate by advancing the theory and utility of Holographic Reduced Representations (HRRs). HRRs are a type of linear, associative memory developed by Plate and are an implementation of Hinton’s reduced representations. HRRs and HRR-like representations have been used to model human memory, to model understanding analogies, and to model the semantics of natural language. However, in previous research, HRRs are restricted to storing and retrieving vectors of random numbers, limiting both the ability of HRRs to model human performance in detail, and the potential applications of HRRs. We delve into the theory of HRRs and develop techniques to store and retrieve images, or other kinds of structured data, in an HRR. We also investigate square matrix representations as an alternative to HRRs, and use iterative training algorithms to improve HRR performance. This work provides a foundation for cognitive modellers and computer scientists to explore new applications of HRRs. / Thesis (Master, Computing) -- Queen's University, 2010-08-10 12:50:04.004

Retrospective revaluation— learning about implied but unpresented cues— poses one of the greatest challenges to classical learning theories. Whereas theorists have revised their models to accommodate revaluation, the empirical reliability of the phenomenon remains contentious. I present two sets of experiments that examine revaluative learning under different but analogous experimental protocols. Results provided mixed empirical evidence that is difficult to interpret in isolation. To address the issue, I apply two computational models to the experiments. An instance-based model of associative learning (Jamieson et al., 2012) predicts retrospective revaluation and anticipates participant behaviour in one set of experiments. An updated classical learning model (Ghirlanda, 2005) fails to predict retrospective revaluation, but anticipates participant behaviour in the other set of experiments. I argue that retrospective revaluation emerges as a corollary of basic memorial processes and discuss the empirical and theoretical implications.