No description available.

The advent of artificial intelligence applications demands for massive amount of data to supplement the training of machine learning models. Traditional machine learning schemes require central processing of large volumes of data that may contain sensitive patterns such as user location, personal information, or transactions history. Federated Learning (FL) has been proposed to complement the traditional centralized methods where multiple local models are trained and aggregated over a centralized cloud server. However, the performance of FL needs to be further improved, since its accuracy is not on par with traditional centralized machine learning approaches. Furthermore, due to the possibility of privacy information leakage, there are not enough clients willing to participate in FL training process. Common practice for the uploaded local models is an evenly weighted aggregation, assuming that each node of the network contributes to advancing the global model equally, which is unfair with higher contribution model owners. This thesis focuses on three aspects of improving a whole federated learning pipeline: client selection; reputation enabled weight aggregation; and incentive mechanism. For client selection, a reputation score consists of evaluation metrics is introduced to eliminate poor performing model contributions. This scheme enhances the original implementation by up to 10% for non-IID datasets. We also reduce the training time of selection scheme by roughly 27.7% compared to the baseline implementation. Then, a reputation-enabled weighted aggregation of the local models for distributed learning is proposed. Thus, the contribution of a local model and its aggregation weight is evaluated and determined by its reputation score, which is formulated as same above. Numerical comparison of the proposed methodology that assigns different aggregation weights based on the accuracy of each model to a baseline that utilizes standard average aggregation weight shows an accuracy improvement of 17.175% over the standard baseline for not independent and identically distributed (non-IID) scenarios for an FL network of 100 participants. Last but not least, for incentive mechanism, we can reward participants based on data quality, data quantity, reputation and resource allocation of participants. In this thesis, we adopt a reputation-aware reverse auction that was earlier proposed to recruit dependable participants for mobile crowdsensing campaigns, and modify that incentive to adapt it to a FL setting where user utility is defined as a function of the assigned payment from the central server and the user’s service cost, such as battery and processor usage. Through numerical results, we show that: 1) the proposed incentive can improve the user utilities when compared to the baseline approaches, 2) platform utility can be maintained at a close value to that under the baselines, 3) the overall test accuracy of the aggregated global model can even slightly improve.

No description available.

No description available.

The fact that some subjects learn both relevant dimensions in a relevant redundant cue concept identification problem has been offered in sudport of the use of a multiple look strategy by subjects. The present study shows that subjects are «o3 i > assarily using a multiple look strategy but rather may be using a one-look strategy to solve the problem. This was shown by asking one group of subjects to stop responding and state their solution to the problem when they felt that they had solved the problem. They then continued responding until they hac completed a fairly large number of consecutive correct responses. At this point they were again quizzed on their solution. A total of 46 subjects were run in this group and of this number, 19 were identified as two cue learners at the end of the criterion run. Of these 19 two cue learners only 5 had learned about the two relevant cues at the solution trial. These results were compared with a group of subjects who solved the problem without being stopped. Of the H6 subjects run in this group 18 were classified as two cue learners at the end of the criterion run. The results are discussed in terms of supporting a one-look interpretation of concept identification learning.

No description available.

No description available.

No description available.

The study explored incidental learning in the workplace. Three research questions guided the study: 1. What is the nature of incidental learning in the workplace? 2. How does professional context impact incidental learning? 3. How do incidental learners know they know in the workplace? A series of three interviews were done with seven human resource professionals and with seven engineers following Seidman's phenomenological interview protocol. The first interview focused on the participant's life history concentrating on the context of the participant's early learning experiences and their professional choices. The second interview provided details of the participant's current incidental learning experiences and an example of their current professional tasks. The third interview provided an opportunity for the participants and me to explore the meaning of their experiences. Analysis of individual experiences was done via profiles, and an analysis of thematic findings was done across all participants. Findings showed that in the "lived world" the experience of the participants and the nature of incidental learning is mediated by the individual's conception of learning and by the individual's learning style. At a professional level, frames and reflection-in and on-action further guide the focus of and validation of the incidental learning. For the researcher -- and perhaps for co-workers or for participants themselves -- incidental learning is easy to overlook; lessons learned often appear to be simply common sense after the fact. This may, in part, be due to the fact that the stories of incidental learning ultimately had successful outcomes. This study confirmed and expanded the importance and impact of context on incidental learning, showing how the elements of an individual's personal and professional context also impact incidental learning. Recommendations for future research and implications for practice were provided. Recommendations for future research included: replicating the study to explore incidental learning in more professions and to explore of the impact of formal higher education on incidental learning. Process recommendations include studying incidental learning as an adjunct to other studies of organizational learning and as a part of an action research project. These methods allow the researcher to study the construct indirectly and as it happens. / Ph. D.

Approaches to workplace learning are continuously evolving to support business objectives but learning and development practitioners are not delivering on their mandate of developing relevant competencies which deliver on strategic objectives. Globally, the proportion of e-Learning to instructor led training is growing and the investment in e-Learning is steadily increasing. Executives expect to see better alignment of e-Learning initiatives and a proven return on investment. In order to earn their place at the executive boardroom, learning and development practitioners need to understand and align their programmes to the context of the business environment in order to positively influence business performance.This research set out to investigate the relationship between the corporate learning environment and e-Learning programme effectiveness using a self-administered questionnaire. The survey was completed by 50 corporate learning and development practitioners. It explored e-Learning programme effectiveness and the configuration of learning environments in relation to a corporate learning environment interconnectedness model proposed in this research. Descriptive statistics, correlation analysis and regression modelling were used to determine the relationship between the environment and e-Learning programme effectiveness. The strongest environmental predictors as well as the current perception of e-Learning programme effectiveness within these environments were also identified.The corporate learning environment was found to be significantly correlated with e-Learning programme effectiveness, specifically in driving higher order benefits of e-Learning programme effectiveness, behaviour change and return on investment. The two strongest predictors of e-Learning programme effectiveness in the corporate learning environment were found to be the definition of clear learning outcomes as well as the provision of opportunities for collaboration in the context of learning. The proposed model of corporate learning environment interconnectedness was also validated and found to be reliable. / Dissertation (MBA)--University of Pretoria, 2012. / Gordon Institute of Business Science (GIBS) / unrestricted