Search

Purpose: The purpose of this paper is to argue that human resource development (HRD) needs to embrace and include futures and foresight learning (FFL) as a new addition to its field of theorising and practice. The question to consider is: How can FFL become a new feature of HRD? A key part of the authors' argument is that the inclusion of FFL will enable HRD to add to the success of any organisation and make a vital contribution to the management of people at work. Design/methodology/approach: This paper firstly considers some of the debates surrounding the meaning of HRD. The authors suggest that instability of the time serves to disturb any comforts that have been created in HRD and that there is a need to consider how there might be different futures for what we still call HRD in research, practice and praxis. This paper then considers how FFL might become one possibility for expanding the existing boundaries of HRD. The authors characterise futures and foresight as a learning process, which provides new but complementary features to what is already considered as HRD. This paper will show how FFL can lead to organisation's success and the way this can be achieved. Findings: There is a wide variety of meanings of the term HRD; however, HRD is still cast as a "weakened profession" which has to play a subservient role to others in the workplace. Over the last 15 years, the expansion of the meaning of HRD has been seen as evidence of its evolving and emerging nature and development based on a co-creation with other disciplines. This creates a space for FFL, defined as an ongoing learning process to find predictable, probable, possible and/or a variety of long-term futures. FFL embraces three key processes of scanning, futuring and reconfiguring, all of which contain a high potential for participants and others to learn as they proceed, providing outcomes at each stage. FFL has been shown to enhance organisation performance and success and HRD interventions can play a key part in implementation. This represents a significant opportunity for the HRD profession to move from weakness towards strength. Research limitations/implications: For HRD researchers, while FFL is not yet on its radar, the authors would argue that the uncertainties of the future require that more attention be given to what might lie ahead. Indeed, HRD researchers need to ask the question: What is the future of HRD research? In addition, if the authors' call for FFL to be included in the practice of HRD, such practice will itself provide new pathways for HRD research. Further research questions might include: To what extent is FFL practiced in organisations and what role do HRD practitioners play in delivery? How does FFL impact on organisation behaviour and outcomes? What new products and services emerge from FFL? What new skills are required to deliver FFL? Can FFL enhance the status of HRD practitioners in the work place and its role in decision-making? and How can the HRD profession develop as a hybrid profession with respect to machine learning (ML)/artificial intelligence (AI)? Practical implications: FFL produces outcomes that have importance for strategy, HRD practitioner can learn to facilitate FFL by action learning and in leadership development programmes. FFL offers a significant opportunity to enhance the importance of HRD in organisations and beyond. FFL offers those involved in HRD a significant opportunity to transfer ideas into practice that have an impact on organisation sustainability. HRD can play a significant role in the design and delivery of ML and AI projects. Originality/value: This paper concludes with a call for embracing FFL as a challenging but important addition to how we talk about learning at work. The authors argue that FFL offers a significant opportunity to enhance the importance of HRD in organisations and beyond. At its centre, FFL involves learning by people, groups, organisations and machines and this has to be of concern to HRD. [ABSTRACT FROM AUTHOR]

Learning style plays an important role in enabling students to have an efficient learning process. This paper proposes an auto-detection model of student learning styles in learning management systems based on student learning activities. A literature review was conducted to investigate the components of online learning activities. The search terms used were "online learning activities", "learning management systems", and "Felder-Silverman Learning Style Model (FSLSM)." A combination of the search terms above was also executed to enhance the search process. Based on the results of the review, eleven classes of online learning activities were identified, namely forum, chat, mail, reading materials, exam delivery time, exercises, access to examples, answer changes, learning materials, exam results, and information access. The online learning activities identified were then mapped to the Felder-Silverman model based on four model dimensions: processing, perception, input, and understanding. The proposed model shows the attributes of the online learning activities based on the dimensions in the FSLSM. The proposed model can assist educators to improve learning content according to the suitability of students and recommend appropriate learning materials to students based on their characteristics and preferences. Future studies include the use of machine learning algorithms such as decision trees to auto-detect student learning styles in learning management systems. [ABSTRACT FROM AUTHOR]

Researchers are defining new types of interactions between humans and machine learning algorithms generically called human-in-the-loop machine learning. Depending on who is in control of the learning process, we can identify: active learning, in which the system remains in control; interactive machine learning, in which there is a closer interaction between users and learning systems; and machine teaching, where human domain experts have control over the learning process. Aside from control, humans can also be involved in the learning process in other ways. In curriculum learning human domain experts try to impose some structure on the examples presented to improve the learning; in explainable AI the focus is on the ability of the model to explain to humans why a given solution was chosen. This collaboration between AI models and humans should not be limited only to the learning process; if we go further, we can see other terms that arise such as Usable and Useful AI. In this paper we review the state of the art of the techniques involved in the new forms of relationship between humans and ML algorithms. Our contribution is not merely listing the different approaches, but to provide definitions clarifying confusing, varied and sometimes contradictory terms; to elucidate and determine the boundaries between the different methods; and to correlate all the techniques searching for the connections and influences between them. [ABSTRACT FROM AUTHOR]

Sensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to continuously learn and adapt, while retaining the knowledge of previously learned activities, and without failing to highlight novel, and therefore potentially risky, behaviours. In this paper, we propose a method based on compression that can incrementally learn new behaviours, while retaining prior knowledge. Evaluation was conducted on three publicly available smart home datasets. [ABSTRACT FROM AUTHOR]

Training data creation is increasingly a key bottleneck for developing machine learning, especially for deep learning systems. Active learning provides a cost-effective means for creating training data by selecting the most informative instances for labeling. Labels in real applications are often collected from crowdsourcing, which engages online crowds for data labeling at scale. Despite the importance of using crowdsourced data in the active learning process, an analysis of how the existing active learning approaches behave over crowdsourced data is currently missing. This paper aims to fill this gap by reviewing the existing active learning approaches and then testing a set of benchmarking ones on crowdsourced datasets. We provide a comprehensive and systematic survey of the recent research on active learning in the hybrid human–machine classification setting, where crowd workers contribute labels (often noisy) to either directly classify data instances or to train machine learning models. We identify three categories of state of the art active learning methods according to whether and how predefined queries employed for data sampling, namely fixed-strategy approaches, dynamic-strategy approaches, and strategy-free approaches. We then conduct an empirical study on their cost-effectiveness, showing that the performance of the existing active learning approaches is affected by many factors in hybrid classification contexts, such as the noise level of data, label fusion technique used, and the specific characteristics of the task. Finally, we discuss challenges and identify potential directions to design active learning strategies for hybrid classification problems. [ABSTRACT FROM AUTHOR]

Data generation and labeling are often expensive in robot learning. Preference-based learning is a concept that enables reliable labeling by querying users with preference questions. Active querying methods are commonly employed in preference-based learning to generate more informative data at the expense of parallelization and computation time. In this article, we develop a set of novel algorithms, batch active preference-based learning methods, that enable efficient learning of reward functions using as few data samples as possible while still having short query generation times and also retaining parallelizability. We introduce a method based on determinantal point processes for active batch generation and several heuristic-based alternatives. Finally, we present our experimental results for a variety of robotics tasks in simulation. Our results suggest that our batch active learning algorithm requires only a few queries that are computed in a short amount of time. We showcase one of our algorithms in a study to learn human users' preferences. [ABSTRACT FROM AUTHOR]

In many engineered systems, optimization is used for decision making at time scales ranging from real-time operation to long-term planning. This process often involves solving similar optimization problems over and over again with slightly modified input parameters, often under tight latency requirements. We consider the problem of using the information available through this repeated solution process to learn important characteristics of the optimal solution as a function of the input parameters. Our proposed method is based on learning relevant sets of active constraints, from which the optimal solution can be obtained efficiently. Using active sets as features preserves information about the physics of the system, enables interpretable results, accounts for relevant safety constraints, and is easy to represent and encode. However, the total number of active sets is also very large, as it grows exponentially with system size. The key contribution of this paper is a streaming algorithm that learns the relevant active sets from training samples consisting of the input parameters and the corresponding optimal solution, without any restrictions on the problem type, problem structure or probability distribution of the input parameters. The algorithm comes with theoretical performance guarantees and is shown to converge fast for problem instances with a small number of relevant active sets. It can thus be used to establish simultaneously learn the relevant active sets and the practicability of the learning method. Through case studies in optimal power flow, supply chain planning, and shortest path routing, we demonstrate that often only a few active sets are relevant in practice, suggesting that active sets provide an appropriate level of abstraction for a learning algorithm to target. [ABSTRACT FROM AUTHOR]

Accurate texture classification empowers robots to improve their perception and comprehension of the environment, enabling informed decision-making and appropriate responses to diverse materials and surfaces. Still, there are challenges for texture classification regarding the vast amount of time series data generated from robots' sensors. For instance, robots are anticipated to leverage human feedback during interactions with the environment, particularly in cases of misclassification or uncertainty. With the diversity of objects and textures in daily activities, Active Learning (AL) can be employed to minimize the number of samples the robot needs to request from humans, streamlining the learning process. In the present work, we use AL to select the most informative samples for annotation, thus reducing the human labeling effort required to achieve high performance for classifying textures. We also use a sliding window strategy for extracting features from the sensor's time series used in our experiments. Our multi-class dataset (e.g., 12 textures) challenges traditional AL strategies since standard techniques cannot control the number of instances per class selected to be labeled. Therefore, we propose a novel class-balancing instance selection algorithm that we integrate with standard AL strategies. Moreover, we evaluate the effect of sliding windows of two-time intervals (3 and 6 s) on our AL Strategies. Finally, we analyze in our experiments the performance of AL strategies, with and without the balancing algorithm, regarding fl-score, and positive effects are observed in terms of performance when using our proposed data pipeline. Our results show that the training data can be reduced to 70% using an AL strategy regardless of the machine learning model and reach, and in many cases, surpass a baseline performance. Finally, exploring the textures with a 6-s window achieves the best performance, and using either Extra Trees produces an average fl-score of 90.21% in the texture classification data set. [ABSTRACT FROM AUTHOR]

When performing learning tasks in pervasive environments, the main challenge arises from the need of combining federated and continual settings. The former comes from the massive distribution of devices with privacy-regulated data. The latter is required by the low resources of the participating devices, which may retain data for short periods of time. In this paper, we propose a setup for learning with Echo State Networks (ESNs) in pervasive environments. Our proposal focuses on the use of Intrinsic Plasticity (IP), a gradient-based method for adapting the reservoir's non-linearity. First, we extend the objective function of IP to include the uncertainty arising from the distribution of the data over space and time. Then, we propose Federated Intrinsic Plasticity (FedIP), which is intended for client–server federated topologies with stationary data, and adapts the learning scheme provided by Federated Averaging (FedAvg) to include the learning rule of IP. Finally, we further extend this algorithm for learning to Federated Continual Intrinsic Plasticity (FedCLIP) to equip clients with CL strategies for dealing with continuous data streams. We evaluate our approach on an incremental setup built upon real-world datasets from human monitoring, where we tune the complexity of the scenario in terms of the distribution of the data over space and time. Results show that both our algorithms improve the representation capabilities and the performance of the ESN, while being robust to catastrophic forgetting. • Reservoir computing is very effective for continual and distributed learning. • Adding continual and federated learning to echo state networks. • Unsupervised federated and continual adaptation of reservoir. • Federated and continual learning for human action recognition and stress prediction. [ABSTRACT FROM AUTHOR]

In many industrial or healthcare contexts, keeping track of the number of people is essential. Radar systems, with their low overall cost and power consumption, enable privacy-friendly monitoring in many use cases. Yet, radar data are hard to interpret and incompatible with most computer vision strategies. Many current deep learning-based systems achieve high monitoring performance but are strongly context-dependent. In this work, we show how context generalization approaches can let the monitoring system fit unseen radar scenarios without adaptation steps. We collect data via a 60 GHz frequency-modulated continuous wave in three office rooms with up to three people and preprocess them in the frequency domain. Then, using meta learning, specifically the Weighting-Injection Net, we generate relationship scores between the few training datasets and query data. We further present an optimization-based approach coupled with weighting networks that can increase the training stability when only very few training examples are available. Finally, we use pool-based sampling active learning to fine-tune the model in new scenarios, labeling only the most uncertain data. Without adaptation needs, we achieve over 80% and 70% accuracy by testing the meta learning algorithms in new radar positions and a new office, respectively. [ABSTRACT FROM AUTHOR]

Human action recognition is an essential process in surveillance video analysis, which is used to understand the behavior of people to ensure safety. Most of the existing methods for HAR use computationally heavy networks such as 3D CNN and two-stream networks. To alleviate the challenges in the implementation and training of 3D deep learning networks, which have more parameters, a customized lightweight directed acyclic graph-based residual 2D CNN with fewer parameters was designed from scratch and named HARNet. A novel pipeline for the construction of spatial motion data from raw video input is presented for the latent representation learning of human actions. The constructed input is fed to the network for simultaneous operation over spatial and motion information in a single stream, and the latent representation learned at the fully connected layer is extracted and fed to the conventional machine learning classifiers for action recognition. The proposed work was empirically verified, and the experimental results were compared with those for existing methods. The results show that the proposed method outperforms state-of-the-art (SOTA) methods with a percentage improvement of 2.75% on UCF101, 10.94% on HMDB51, and 0.18% on the KTH dataset. [ABSTRACT FROM AUTHOR]

Federated learning (FL) guaranteeing data privacy is of great interest in decentralized fault diagnosis. However, limited research attention has been paid to the dynamic domain-shift issue due to varying working conditions. This paper proposes an active federated transfer algorithm based on broad learning to address the domain shift issue in FL. First, a central server dispatches a global model to the source clients for collaborative modeling. Subsequently, the global model is initialized with a federated averaging strategy. Next, the initialized global model is used to annotate emerging signals from the target clients based on an active sampling strategy proposed. Finally, an asynchronous update scheme is designed to adapt the global model to the target domain. The performance of the AFTBL algorithm is validated with three datasets, including 24 centralized- and decentralized-modeling tasks. The computational results indicate that the proposed algorithm is more accurate and efficient than the prevalent algorithms. • The cross-domain incremental federated learning problem is investigated. • An active federated broad transfer algorithm is proposed for fault diagnosis. • Automated data annotation and selection are proposed for incremental model update. [ABSTRACT FROM AUTHOR]

Peer learning is a process where one or more students teach other students and provides support throughout the learning process. Active learning is a process of learning concepts through thinking, discussing, investigating, and creating. In order to improve the learning of students in the concept of "problem solving using C programming," peer and active learning approaches are implemented by forming groups. The general four methods for peer active learning, such as think-pair-share, the zig-zag method, the coding test, and mini project, are chosen as activities for the students. An unsupervised machine learning algorithm is used to create clusters of students based on pretest and posttest scores. With the help of the K-Means clustering technique, the increased change in student performance after peer active learning approaches is clearly visible. [ABSTRACT FROM AUTHOR]

The cerebellum is considered a "learning machine" essential for time interval estimation underlying motor coordination and other behaviors. Theoretical work has proposed that the cerebellum's input recipient structure, the granule cell layer (GCL), performs pattern separation of inputs that facilitates learning in Purkinje cells (P-cells). However, the relationship between input reformatting and learning has remained debated, with roles emphasized for pattern separation features from sparsification to decorrelation. We took a novel approach by training a minimalist model of the cerebellar cortex to learn complex time-series data from time-varying inputs, typical during movements. The model robustly produced temporal basis sets from these inputs, and the resultant GCL output supported better learning of temporally complex target functions than mossy fibers alone. Learning was optimized at intermediate threshold levels, supporting relatively dense granule cell activity, yet the key statistical features in GCL population activity that drove learning differed from those seen previously for classification tasks. These findings advance testable hypotheses for mechanisms of temporal basis set formation and predict that moderately dense population activity optimizes learning. [ABSTRACT FROM AUTHOR]