Boosting-based transfer learning for multi-view head-pose classification from surveillance videos

This work proposes a boosting-based transfer learning approach for head-pose classification from multiple, low-resolution views. Head-pose classification performance is adversely affected when the source (training) and target (test) data arise from different distributions (due to change in face appearance, lighting, etc). Under such conditions, we employ Xferboost, a Logitboost-based transfer learning framework that integrates knowledge from a few labeled target samples with the source model to effectively minimize misclassifications on the target data. Experiments confirm that the Xferboost framework can improve classification performance by up to 6%, when knowledge is transferred between the CLEAR and FBK four-view headpose datasets.

Exploring Transfer Learning Approaches for Head Pose Classification from Multi-view Surveillance Images

Head pose classification from surveillance images acquired with distant, large field-of-view cameras is difficult as faces are captured at low-resolution and have a blurred appearance. Domain adaptation approaches are useful for transferring knowledge from the training (source) to the test (target) data when they have different attributes, minimizing target data labeling efforts in the process. This paper examines the use of transfer learning for efficient multi-view head pose classification with minimal target training data under three challenging situations: (i) where the range of head poses in the source and target images is different, (ii) where source images capture a stationary person while target images capture a moving person whose facial appearance varies under motion due to changing perspective, scale and (iii) a combination of (i) and (ii). On the whole, the presented methods represent novel transfer learning solutions employed in the context of multi-view head pose classification. We demonstrate that the proposed solutions considerably outperform the state-of-the-art through extensive experimental validation. Finally, the DPOSE dataset compiled for benchmarking head pose classification performance with moving persons, and to aid behavioral understanding applications is presented in this work.

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.

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.

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 transfer in multinational companies:Explaining inter-organisation variation

This article addresses the extent to which multinational companies (MNCs) in Ireland deploy practices aimed at the transfer of learning in their operations and the factors explaining inter-organisation variation in so doing. Using data from 260 MNCs, we find that comparatively large numbers of firms deploy practices to transfer learning in their Irish operations. Most notably, we find that almost half of all MNCs have a formal policy on organisational learning, while more than six in every ten MNCs in Ireland utilise three or more learning transfer mechanisms. In investigating inter-organisation variation with respect to these, we test a number of hypotheses involving nationality, sectoral, MNC (e.g. organisation structure) and HR factors. Our results show that the presence of international HR structures is a significant factor in explaining learning transfer in MNCs. We also find support that employment size, sector and integration between the MNC's global operations are useful variables in explaining variation in the deployment of practices on learning transfer in MNCs. © 2009 Blackwell Publishing Ltd.

Analyzing the learning of the taking personal and social responsibility model within a new physical education undergraduate degree program in El Salvador

EI Salvador presents an unfortunate history that includes a military regime and a civil war that together created a legacy of violence in which the country still struggle nowadays. Salud Escolar Integral (SEI) was created in 2005 as a program to combat youth violence throughout the re-formulation of physical education (PE) classes in public schools, promoting life skills learning that supports the resolution of conflicts with nonviolent ways. In 2007, SEI supported the creation of a physical e~ucation teacher education (PETE) degree at the Universidad Pedag6gica de EI Salvador (UPES), having the goal to assist pre-service teachers with a better understanding of humanistic principles. The present research analyzed if after attending all three years ofUPES PETE program, students presented high self-perception levels of competence and confidence related to attitude, skills and knowledge to teach PE within humanistic principles. Taking Personal and Social Responsibility (TPSR) was the theoretical framework used to analyze the development of humanistic principles. The study had a mixed-method longitudinal design that included questionnaires, reflection templates and interviews. In conclusion, although it is suggested that UPES should provide better support for the development of the teaching principles of empowering students and transfer learning, most of the humanistic principles were highly promoted by the program. At last, it is suggested that future research should track teachers' progress while teaching in schools, in order to analyze if the theory of promoting humanistic principles have also become a daily practice.

Action learning: how learning transfers from entrepreneurs to small firms

The paper presents research with small and medium enterprise (SME) owners who have participated in a leadership development programme. The primary focus of the paper is on learning transfer and factors affecting it, arguing that entrepreneurs must engage in ‘action’ in order to ‘learn’ and that under certain conditions they may transfer learning to their firm. The paper draws on data from 19 focus groups undertaken from 2010 to 2012, involving 51 participants in the LEAD Wales programme. It considers the literatures exploring learning transfer and develops a conceptual framework, outlining four areas of focus for entrepreneurial learning. Utilising thematic analysis, it describes and evaluates what (actual facts and information) and how (techniques, styles of learning) participants transfer and what actions they take to improve the business and develop their people. The paper illustrates the complex mechanisms involved in this process and concludes that action learning is a method of facilitating entrepreneurial learning which is able to help address some of the problems of engagement, relevance and value that have been highlighted previously. The paper concludes that the efficacy of an entrepreneurial learning intervention in SMEs may depend on the effectiveness of learning transfer.

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.

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.

Nonnegative shared subspace learning and its application to social media retrieval

Although tagging has become increasingly popular in online image and video sharing systems, tags are known to be noisy, ambiguous, incomplete and subjective. These factors can seriously affect the precision of a social tag-based web retrieval system. Therefore improving the precision performance of these social tag-based web retrieval systems has become an increasingly important research topic. To this end, we propose a shared subspace learning framework to leverage a secondary source to improve retrieval performance from a primary dataset. This is achieved by learning a shared subspace between the two sources under a joint Nonnegative Matrix Factorization in which the level of subspace sharing can be explicitly controlled. We derive an efficient algorithm for learning the factorization, analyze its complexity, and provide proof of convergence. We validate the framework on image and video retrieval tasks in which tags from the LabelMe dataset are used to improve image retrieval performance from a Flickr dataset and video retrieval performance from a YouTube dataset. This has implications for how to exploit and transfer knowledge from readily available auxiliary tagging resources to improve another social web retrieval system. Our shared subspace learning framework is applicable to a range of problems where one needs to exploit the strengths existing among multiple and heterogeneous datasets.