“A Building that Recalls” is a report that offers up the provocation that figures of housing are prevalent throughout histories of rhetorics connected to memory, and are of great ethical significance. One can turn to three key examples to demonstrate this thesis: Martin Heidegger’s Black Forest “Hut,” Michel Foucault’s “Panopticon,” and Lebbeus Woods’ “Scar” and “Scab” architectural designs. Heidegger’s hut reminds its viewers that a place of dwelling can serve both as a lesson in the dangers of nationalist memory-politics, and simultaneously as a model for overcoming fascism in oneself. Foucault’s Panopticon model reveals that the rooting out and “forgetting” of burned in social norms is difficult because subjectivity is a social fabrication. Finally, Lebbeus Wood’s “Scar” and “Scab” designs (accompanied with commentary by Victor Vitanza) show how an affirmative forgetting is possible in the wake of tyranny and trauma. / text

Through diachronic examination of communicative acts, this dissertation explores intertwined processes of social memory, remembering, forgetting and place-making that have involved the former Cook County Hospital, located in Chicago, Illinois. With emphasis on narratives, nomination practices, and social contexts, this project illuminates and examines discourse conveyed during three 'moments' of material rupture and transformation of the Cook County Hospital facilities. A central perspective of this dissertation is that discourse articulated during these 'moments' reveals social remembering and memory with regard to place-making involving the former hospital and Main Building, as well as evidences social forgetting occurring between the years 1873 to 2007. For purposes of this project, three 'moments' of material transformation are regarded as bracketed by the years 1873 through 1876, the years 1910 through 1914, and the year 2002 through a year that is, as of yet, undetermined. These 'moments' were identified through examination of articulation and recoding of labels that could be regarded more informal than official for the county hospital facilities. This project illuminates the importance and complexity of naming in place-making processes, and the necessity of diachronic approaches to exploring social remembering and forgetting relevant to place. In highlighting the fluidity of social remembering, this dissertation emphasizes value of making primary source materials accessible in public domain, for future generations. Further illuminated is the value of newsprint as channels of mass communication through which aspects of social remembering, forgetting, and place-making can be investigated. Whether to demolish or re-use the now vacant Main Building became an issue of public contestation in 2002. This project was inspired, in part, by contestation concerning the proposed demolition, by senses of the city, and by the diverse and proliferating interdisciplinary ‘corpus’ of scholarship that articulates notions of social memory, remembering, and forgetting. / text

Recent literature suggests that typical forms of encoding (i.e., elaboration) are obsolete as compared to rating words based on survival relevance (Nairne, Thompson, and Pandeirada, 2007). Information encoded using survival ratings have produced superior recall despite manipulations to quell its effect. The current study examined whether survival processing is protected against forgetting. Our results suggest that targets studied under survival processing are not immune from retrieval blocking and RI effects. No effects of survival processing were obtained.

Cross-domain intrusion detection, a critical component of cybersecurity, involves evaluating the performance of neural networks across diverse datasets or databases. The ability of intrusion detection systems to effectively adapt to new threats and data sources is paramount for safeguarding networks and sensitive information. This research delves into the intricate world of cross-domain intrusion detection, where neural networks must demonstrate their versatility and adaptability. The results of our experiments expose a significant challenge: the phenomenon known as catastrophic forgetting. This is the tendency of neural networks to forget previously acquired knowledge when exposed to new information. In the context of intrusion detection, it means that as models are sequentially trained on different intrusion detection datasets, their performance on earlier datasets degrades drastically. This degradation poses a substantial threat to the reliability of intrusion detection systems. In response to this challenge, this research investigates potential solutions to mitigate the effects of catastrophic forgetting. We propose the application of continual learning techniques as a means to address this problem. Specifically, we explore the Elastic Weight Consolidation (EWC) algorithm as an example of preserving previously learned knowledge while allowing the model to adapt to new intrusion detection tasks. By examining the performance of neural networks on various intrusion detection datasets, we aim to shed light on the practical implications of catastrophic forgetting and the potential benefits of adopting EWC as a memory-preserving technique. This research underscores the importance of addressing catastrophic forgetting in cross-domain intrusion detection systems. It provides a stepping stone for future endeavours in enhancing multi-task learning and adaptability within the critical domain of intrusion detection, ultimately contributing to the ongoing efforts to fortify cybersecurity defences.

No description available.

No description available.

No description available.

"Recommender systems are being widely applied in many E-commerce sites to suggest products, services, and information items to potential users. Collabora-tive filtering systems, the most successful recommender system technology to date, help people make choices based on the opinions of other people. While collaborative filtering systems have been a substantial success, there are sev-eral problems that researchers and commercial applications have identified: the early rater problem, the sparsity problem, and the large scale problem. Moreover, existing collaborative filtering systems do not consider data re-cency. For this reason, if a user's preferences have changed over time, the sys-tems might not recognize it quickly. This thesis studies how to apply data re-cency to collaborative filtering systems to get more predictive accuracy. We define the data recency problem as the negative impact of old data on the pre-dictive accuracy of collaborative filtering systems. In order to mitigate this shortcoming, the combinations of time-based forgetting mechanisms, pruning and non-pruning strategies and linear and kernel functions, are utilized to ap-ply weights. A clustering technique is employed to detect the user's changing preferences. We apply our research approach to the DeliBook dataset. The goal of our experiments is to show that our algorithm that incorporates tempo-ral factors provides better recommendations than existing methods."

An accurate estimate of the mass of a passenger vehicle is important for several safety systems and environmental aspects. In this thesis, an algorithm for estimating the mass of a passenger vehicle using the recursive least squares methodis presented. The algorithm is based on a physical model of the vehicle and is designed to be able to run in real-time onboard a vehicle and uses the wheel torque signal calculated in the electrical control unit in the engine. Therefore no estimation of the powertrain is needed. This is one contribution that distinguishes this thesis from previous work on the same topic, which has used the engine torque. The benefit of this is that no estimation of the dynamics in the powertrain is needed. The drawback of using this method is that the algorithm is dependenton the accuracy of the estimation done in the engine electrical control unit. Two different versions of the recursive least squares method (RLS) have been developed - one with a single forgetting factor and one with two forgetting factors. The estimation performance of the two versions are compared on several different real-world driving scenarios, which include driving on country roads, highways, and city roads, and different loads in the vehicle. The algorithm with a single forgetting factor estimates the mass with an average error for all tests of 4.42% and the algorithm with multiple forgetting factors estimates the mass with an average error of 4.15 %, which is in line with state-of-the-art algorithms that are presented in other studies. In a sensitivity analysis, it is shown that the algorithms are robust to changes in the drag coefficient. The single forgetting factor algorithm is robust to changes in the rolling resistance coefficient whereas the multiple forgetting factor algorithm needs the rolling resistance coefficient to be estimated with fairly good accuracy. Both versions of the algorithm need to know the wheel radius with an accuracy of 90 %. The results show that the algorithms estimate the mass accurately for all three different driving scenarios and estimate highway roads best with an average error of 2.83 % and 2.69 % for the single forgetting factor algorithm and the multiple forgetting factor algorithm, respectively. The results indicate it is possible to use either algorithm in a real-world scenario, where the choice of which algorithm depends on sought-after robustness.

Image classification is an area of computer science with many areas of application. One key issue with using Artificial Neural Networks (ANN) for image classification is the phenomenon of Catastrophic Forgetting when training tasks sequentially (i.e Continual Learning). This is when the network quickly looses its performance on a given task after it has been trained on a new task. Elastic Weight Consolidation (EWC) has previously been proposed as a remedy to lessen the effects of this phenomena through the use of a loss function which utilizes a Fisher Information Matrix. We want to explore and establish if this still holds true for modern network architectures, and to what extent this can be applied using today’s state- of- the- art networks. We focus on applying this approach on tasks within the same dataset. Our results indicate that the approach is feasible, and does in fact lessen the effect of Catastrophic Forgetting. These results are achieved, however, at the cost of much longer execution times and time spent tuning the hyper- parameters. / Bildklassifiering är ett område inom dataologi med många tillämpningsområden. En nyckelfråga när det gäller användingen av Artificial Neural Networks (ANN) för bildklassifiering är fenomenet Catastrophic Forgetting. Detta inträffar när ett nätverk tränas sekventiellt (m.a.o. Continual Learning). Detta innebär att nätverket snabbt tappar prestanda för en viss uppgift efter att den har tränats på en ny uppgift. Elastic Weight Consolidation (EWC) har tidigare föreslagits som ett lindring genom applicering av en förlustfunktion som använder Fisher Information Matrix. Vi vill utforska och fastställa om detta fortfarande gäller för moderna nätverksarkitekturer, och i vilken utsträckning det kan tillämpas. Vi utför metoden på uppgifter inom en och samma dataset. Våra resultat visar att metoden är genomförbar och har en minskande effekt på Catastrophic Forgetting. Dessa resultat uppnås dock på bekostnad av längre körningstider och ökad tidsåtgång för val av hyperparametrar.