Transfer learning using the online Fuzzy Min-Max neural network

In this paper, we present an empirical analysis on transfer learning using the Fuzzy Min–Max (FMM) neural network with an online learning strategy. Three transfer learning benchmark data sets, i.e., 20 Newsgroups, WiFi Time, and Botswana, are used for evaluation. In addition, the data samples are corrupted with white Gaussian noise up to 50 %, in order to assess the robustness of the online FMM network in handling noisy transfer learning tasks. The results are analyzed and compared with those from other methods. The outcomes indicate that the online FMM network is effective for undertaking transfer learning tasks in noisy environments.

Transfer learning using the online FMM model

In this paper, we present an analysis on transfer learning using the Fuzzy Min-Max (FMM) neural network with an online learning strategy. Transfer learning leverages information from the source domain in solving problems in the target domain. Using the online FMM model, the data samples are trained one at a time. In order to evaluate the online FMM model, a transfer learning data set, based on data samples collected from real landmines, is used. The experimental results of FMM are analyzed and compared with those from other methods in the literature. The outcomes indicate that the online FMM model is effective for undertaking transfer learning tasks.

Regularized nonnegative shared subspace learning

Joint modeling of related data sources has the potential to improve various data mining tasks such as transfer learning, multitask clustering, information retrieval etc. However, diversity among various data sources might outweigh the advantages of the joint modeling, and thus may result in performance degradations. To this end, we propose a regularized shared subspace learning framework, which can exploit the mutual strengths of related data sources while being immune to the effects of the variabilities of each source. This is achieved by further imposing a mutual orthogonality constraint on the constituent subspaces which segregates the common patterns from the source specific patterns, and thus, avoids performance degradations. Our approach is rooted in nonnegative matrix factorization and extends it further to enable joint analysis of related data sources. Experiments performed using three real world data sets for both retrieval and clustering applications demonstrate the benefits of regularization and validate the effectiveness of the model. Our proposed solution provides a formal framework appropriate for jointly analyzing related data sources and therefore, it is applicable to a wider context in data mining.

An online transfer learning RBF neural network for cross domain data classification

In this paper, a Radial Basis Function Network (RBFN) trained with the Dynamic Decay Adjustment (DDA) algorithm (i.e., RBFNDDA) is deployed as an incremental learning model for tackling transfer learning problems. An online learning strategy is exploited to allow the RBFNDDA model to transfer knowledge from one domain and applied to classification tasks in a different yet related domain. An experimental study is carried out to evaluate the effectiveness of the online RBFNDDA model using a benchmark data set obtained from a public domain. The results are analyzed and compared with those from other methods. The outcomes positively reveal the potentials of the online RBFNDDA model in handling transfer learning tasks. © 2014 The authors and IOS Press. All rights reserved.

Young children's transfer of learning from a touchscreen device

Because young children are devoting increasing time to playing on handheld touchscreen devices, understanding children's ability to learn from this activity is important. Through two experiments we examined the ability of 4- to 6-year-old children to learn how to solve a problem (Tower of Hanoi) on a touchscreen device and subsequently apply this learning in their interactions with physical objects. The results were that participants demonstrated significant improvement at solving the task irrespective of the modality (touchscreen vs. physical version) with which they practiced. Moreover, children's learning on the touchscreen smoothly transferred to a subsequent attempt on the physical version. We conclude that, at least with respect to certain activities, children are quite capable of transferring learning from touchscreen devices. This result highlights the limitations of generalizing across screen-based activities (e.g., "screen time") in discussing the effects of media on young children's development.

Multiple task transfer learning with small sample sizes

Prognosis, such as predicting mortality, is common in medicine. When confronted with small numbers of samples, as in rare medical conditions, the task is challenging. We propose a framework for classification with data with small numbers of samples. Conceptually, our solution is a hybrid of multi-task and transfer learning, employing data samples from source tasks as in transfer learning, but considering all tasks together as in multi-task learning. Each task is modelled jointly with other related tasks by directly augmenting the data from other tasks. The degree of augmentation depends on the task relatedness and is estimated directly from the data. We apply the model on three diverse real-world data sets (healthcare data, handwritten digit data and face data) and show that our method outperforms several state-of-the-art multi-task learning baselines. We extend the model for online multi-task learning where the model parameters are incrementally updated given new data or new tasks. The novelty of our method lies in offering a hybrid multi-task/transfer learning model to exploit sharing across tasks at the data-level and joint parameter learning.

A new transfer learning framework with application to model-agnostic multi-task learning

Learning from small number of examples is a challenging problem in machine learning. An effective way to improve the performance is through exploiting knowledge from other related tasks. Multi-task learning (MTL) is one such useful paradigm that aims to improve the performance through jointly modeling multiple related tasks. Although there exist numerous classification or regression models in machine learning literature, most of the MTL models are built around ridge or logistic regression. There exist some limited works, which propose multi-task extension of techniques such as support vector machine, Gaussian processes. However, all these MTL models are tied to specific classification or regression algorithms and there is no single MTL algorithm that can be used at a meta level for any given learning algorithm. Addressing this problem, we propose a generic, model-agnostic joint modeling framework that can take any classification or regression algorithm of a practitioner’s choice (standard or custom-built) and build its MTL variant. The key observation that drives our framework is that due to small number of examples, the estimates of task parameters are usually poor, and we show that this leads to an under-estimation of task relatedness between any two tasks with high probability. We derive an algorithm that brings the tasks closer to their true relatedness by improving the estimates of task parameters. This is achieved by appropriate sharing of data across tasks. We provide the detail theoretical underpinning of the algorithm. Through our experiments with both synthetic and real datasets, we demonstrate that the multi-task variants of several classifiers/regressors (logistic regression, support vector machine, K-nearest neighbor, Random Forest, ridge regression, support vector regression) convincingly outperform their single-task counterparts. We also show that the proposed model performs comparable or better than many state-of-the-art MTL and transfer learning baselines.

Flexible transfer learning framework for bayesian optimisation

Bayesian optimisation is an efficient technique to optimise functions that are expensive to compute. In this paper, we propose a novel framework to transfer knowledge from a completed source optimisation task to a new target task in order to overcome the cold start problem. We model source data as noisy observations of the target function. The level of noise is computed from the data in a Bayesian setting. This enables flexible knowledge transfer across tasks with differing relatedness, addressing a limitation of the existing methods. We evaluate on the task of tuning hyperparameters of two machine learning algorithms. Treating a fraction of the whole training data as source and the whole as the target task, we show that our method finds the best hyperparameters in the least amount of time compared to both the state-of-art and no transfer method.

Multi-task transfer learning for in hospital-death prediction for ICU patients

Multi-Task Transfer Learning (MTTL) is an efficient approach for learning from inter-related tasks with small sample size and imbalanced class distribution. Since the intensive care unit (ICU) data set (publicly available in Physionet) has subjects from four different ICU types, we hypothesizethat there is an underlying relatedness amongst various ICU types. Therefore, this study aims to explore MTTL model for in-hospital mortality prediction of ICU patients. We used singletask learning (STL) approach on the augmented data as well as individual ICU data and compared the performance with the proposed MTTL model. As a performance measurement metrics, we used sensitivity (Sens), positive predictivity (+Pred), and Score. MTTL with class balancing showed the best performance with score of 0.78, 0.73, o.52 and 0.63 for ICU type 1(Coronary care unit), 2 (Cardiac surgery unit), 3 (Medical ICU) and 4 (Surgical ICU) respectively. In contrast the maximum score obtained using STL approach was 0.40 for ICU type 1 & 2. These results indicates that the performance of in-hospital mortality can be improved using ICU type information and by balancing the ’non-survivor’ class. The findings of the study may be useful for quantifying the quality of ICU care, managing ICU resources and selecting appropriate interventions.

Learning to minimize energy costs and maximize mechanical work in a bimanual coordination task

The authors addressed the hypothesis that economy in motor coordination is a learning phenomenon realized by both reduced energy cost for a given workload and more external work at the same prepractice metabolic and attentional energy expenditure. "Self-optimization" of movement parameters has been proposed to reflect learned motor adaptations that minimize energy costs. Twelve men aged 22.3 [+ or -] 3.9 years practiced a 90[degrees] relative phase, upper limb, independent ergometer cycling task at 60 rpm, followed by a transfer test of unpracticed (45 and 75 rpm) and self-paced cadences. Performance in all conditions was initially unstable, inaccurate, and relatively high in both metabolic and attentional energy costs. With practice, coordinative stability increased, more work was performed for the same metabolic and attentional costs, and the same work was done at a reduced energy cost. Self-paced cycling was initially below the metabolically optimal, but following practice at 60 rpm was closer to optimal cadence. Given the many behavioral options of the motor system in meeting a variety of everyday movement task goals, optimal metabolic and attentional energy criteria may provide a solution to the problem of selecting the most adaptive coordination and control parameters.

Ensuring quality during monitoring of the learning environment of government primary schools achieved through EUI-PDP for teachers and head teachers

A positive change in the learning environment in schools is visible through ongoing professional development of teachers and administrators. Monitoring the professional development program and providing support to teachers and administrators to transfer their learnings into the school environment ensures some measures of quality. Quality issues led to the launching of the Professional Development Program (PDP) for Primary School Teachers (PSTs) of Sindh by the United Educational Initiative (UEI), a consortium of five Governmental and Non-Governmental Organizations, working under the supervision of Education Sector Reform Assistance (ESRA). Implementation of the UEI-PDP in four districts of Sindh, is ensured by a team of professionals in each district. Recognising that capacity building of district education employees would improve the educational system in the country, 130 Master Trainers were selected, on merit, from the District Education Office for the training of 17,000 teachers and 3000 Head teachers/administrators over a period of two years. This paper developed the design of a Monitoring Process for a Professional Development Program for Primary School Teachers and Administrators. Data was collected through Pre/Post observations, Interviews, Questionnaires and Reports. Such tools make it possible for the monitoring teams to observe, to inquire further, and, along with the Managers, Master Trainers and School Support Team, seek to explain the progress of the program and take corrective action where indicated. Both formative evaluations as well as summative  evaluation techniques are utilized for evaluating the program. The monitoring process that assisted in formative evaluations is described. In order to assist in summative evaluation, data collected through the monitoring process was further developed to categorize the schools where teachers and head teachers are trained. It is hoped that the categorization of the schools may lead to further improvements in those schools which fall in the group for need improvement. It may also initiate further research as to reasons behind why some schools are in the good category and why others fall in the average category.

Designing collaborative e-learning for the net generation

The designer of higher education programs is on the cusp of some very exciting resource development particularly in the area of postgraduate coursework. Part of this is because of the new learner, a millennial or net generation learner who is time-poor, a networker with strong inclinations towards social or community knowledge pooling and a multiple media literacy which is comfortable in virtual worlds and with visual emphasis. The other element is the perceived changing role of the university or higher education in the transfer of knowledge, moving from a transmission or narrative model to learner-centred and performative approaches. This has been highlighted by greater emphasis on experiential learning methodologies, and the development of action learning practices. The nexus of these two influences, the new learner and the higher education response to delivering learning, may be elaborated further from learning theory which seems to be moving beyond social constructivist approaches, or certainly encompassing what is referred to as connectivism.

This may be a new theoretical approach, or it could simply be an organic growth in meeting the needs of large numbers of higher education student participants who perceive a degree as a skills-based workplace preparation. Whatever the theoretical underpinning may be, the large numbers of learners moving to postgraduate coursework or more workplace oriented programs and subjects has thrown out the challenge to instructional designers to provide just-in-time, relevant and socially transferred learning with strong creative and imaginative engagement.

The case studies incorporated in this paper provide two separate approaches to these challenges - one is a workplace oriented postgraduate team project in a Masters in Communication, the other provides a virtual simulation for developing creative and professional writing skills at postgraduate levels. They both provide perspectives on the net generation learner and collaborative and connected learning models.

Scaffolding students' learning in EME150 introduction to learners and learning theory : on looking back

This is a reflective article on the importance scaffolding in the EME 150 unit taught in collaboration with Deakin University Australia. Being the first unit introduced in the second semester of the first academic year, students were given a lot of support to enhance their understanding and learning since this curriculum was solely developed by Deakin University and introduced for the first time in teachers education curriculum. The scaffolding tools discussed in this article enabled students to a) establish deep learning of the theory. b) engage in collaborative and engaged learning which established good ethical relations between students c) transfer learning by applying theory into practice.

Strategies for learning that empower workers and enable organisational achievement

This research found that : Learning that is part of an existing worker traineeship program empowers workers and enables organisational achievement. The organisation is not yet ready to utilise all the empowered workers who successfully complete the learning program. The prevailing management systems and work structures govern the degree to which the workers can transfer their newly-learned skills to the workplace.

Continuous product innovation : learning behaviours and knowledge management

The research reported in this paper considers Product Innovation from a broader perspective than that of the isolated NPD (New Product Development) project commonly discussed in the literature. In this perspective, Product Innovation is a continuous and cross-functional process involving the sharing and transfer of knowledge within the many steps of the innovation process, and the integration of a growing number of different competencies inside and outside the organisational boundaries. This paper examines two in-depth case studies that were carried out to establish if and how learning occurred within companies developing new products. Based on a model developed as part of a joint Euro-Australian research project, the way in which the selected companies share and transfer knowledge and learning experiences during their product innovation processes have been examined and analysed. This model uses a number of interrelated variables including performance, behaviours and levers to stimulate improvement, contingencies, and learning/innovation capabilities to describe the learning and knowledge transfer in product innovation processes within the case studies. This paper discusses some of the skills the research has identified that managers need to enable their companies to gain a competitive advantage through improved product innovation. The ongoing research has developed, tested and disseminated a computer-based methodology to assess organisational knowledge capture and transfer in the new product development process. The research is part of the Euro-Australian co-operation project known as CIMA (Continuous Improvement and Product Innovation Management).