Adaptive Learning Framework Research Articles

A generalized adaptive robust distance metric driven smooth regularization learning framework for pattern recognition

In this work, we propose a novel generalized adaptive robust distance metric called Lδ(u). Compared with other distance metrics, Lδ(u) has some desirable salient properties, such as symmetry, boundedness, robustness, nonconvexity, and adaptivity, with both first-order and higher-order moments from samples. On the other hand, Lδ(u) can pick different robust distance metrics for different learning tasks during the learning process by the adaptive parameter δ. Furthermore, we apply Lδ(u) to twin extreme learning machine (TELM) and develop an smooth regularized TELM learning framework for supervised and semi-supervised classification. By introducing the structural risk minimization (SRM) principle and smoothing techniques, the learning framework perfectly overcomes the computational burden associated with the matrix inversion operation required during TELM solving, while also significantly improving performance. More importantly, the proposed learning framework not only improves the robustness of TELM, but also can effectively use the geometric information of the marginal distribution embedded in the unlabeled samples to construct a more reasonable classifier. Finally, the globally convergent and quadratic convergent fast Newton-Armijo algorithm and DC (difference of convex functions) programming algorithm (DCA) are designed to solve the proposed methods. Experimental results demonstrate the effectiveness and robustness of our methods.

Adaptive Learning Framework (Alef) in UAE Public Schools from the Parents’ Perspective

This study aimed to evaluate the Adaptive Learning Framework (Alef) platform and determine how parents perceive the implementation of such a program to support their children’s learning. Alef is a smart learning program that is mandated in United Arab Emirates (UAE) public schools to promote student-centered, interactive, and differentiated learning and personalized experiences. The participants were parents of students enrolled in grades 9–12 in UAE public high schools. The study used semi-structured interviews to gather qualitative data to delve deeply into parents’ perceptions of how Alef supports their children’s learning. The results showed that Alef offers stimulating and engaging educational experiences and encourages independent learning. It was found that students’ learning was bolstered when using Alef. In addition, the results indicated the existence of some challenges stemming from the usage of Alef that could have an impact on students’ learning and motivation and, ultimately, the sustainability of such a program. Recommendations are provided to overcome these challenges.

Rationality-bounded adaptive learning in multi-agent dynamic games

This paper presents an adaptive learning framework that aims to enable agents with bounded rationality to learn from dynamic games and making decisions accordingly. Within this framework, agents lack complete knowledge of future payoffs but are capable of forming beliefs based on their recognitive abilities and past experiences. Each region involved dynamically adjusts its strategy by considering the tradeoff between the current payoff and belief updated. Based on this premise, we propose the Boundedly Rational Multiagent Learning (BRML) algorithm and provide proof of its convergence under given conditions. To demonstrate the practicality of the BRML algorithm, we employ it to two critical dynamic games: repeated cooperative and non-cooperative games. Our results indicate that groups with bounded rationality can achieve coordination through the behavior of agents with high recognitive ability. Furthermore, Pareto optimality is successfully attained in the coordination problems through the application of this multiagent adaptive learning framework.

An adaptive active learning algorithm with informativeness and representativeness

Active learning focuses on selecting a small subset of the most valuable instances for labeling to learn a highly accurate model. Considering informativeness and representativeness of unlabeled instances is significant for a query, some works have been done about combing informativeness and representativeness criteria. However, most of them are generally in a fixed manner to balance these criteria, and difficult to find suitable sampling strategies and weights of informativeness and representativeness for various datasets. In this paper, an adaptive active learning method ALIR is proposed to address these limitations. Firstly, an adaptive active learning framework is represented, in which the weight of informativeness and representativeness criteria can be dynamically updated by the feedback of previous learning processes. Secondly, by formulating the active learning as a Markov decision process, ALIR can adaptively select the suitable sampling strategies according to the reward of the learning process. Finally, extensive experimental results over several benchmark datasets and two real classification datasets demonstrate that ALIR outperforms several state-of-the-art methods. Different from traditional active learning algorithms, ALIR can adaptively select sampling strategies and adjust the weights simultaneously, which helps it more feasible in the application.

Adaptive learning-driven high-throughput synthesis of oxygen reduction reaction Fe–N–C electrocatalysts

Reducing human reliance on inefficient energy systems and fossil fuels has become more urgent due to the consequences of global climate change. However, traditional trial-and-error approaches have hampered our ability to accelerate the discovery and implementation of functional materials for efficient energy conversion devices, such as polymer electrolyte fuel cells (PEFCs). To address this, we develop an adaptive learning framework that integrates machine learning and state-of-the-art capabilities in high-throughput synthesis to achieve expedited optimization of iron-nitrogen-carbon PEFC oxygen reduction reaction (ORR) electrocatalysts. We use statistical inference, uncertainty quantification, and global optimization to build a computational design-of-experiment tool that identifies the optimum compositions to be investigated next to reduce the demands placed on experimental materials discovery. We benchmark the ability of the proposed strategy to discover optimum catalyst synthesis conditions in a six-dimensional search space when starting with a thirty-six-sample database. By following the adaptive learning strategy, we synthesize fourteen new catalysts from approximately ten billion unique compositions and discover four catalysts that outperform all original samples. The best machine learning-optimized catalyst is 33% more active than the highest-performing one in the initial database, showing an ORR activity seven times larger than those typically reported for the same class of materials.

Adaptive Granulation-Based Convolutional Neural Networks With Single Pass Learning for Remote Sensing Image Classification

Convolutional neural networks (CNNs) with the characteristics like spatial filtering, feed-forward mechanism, and back propagation-based learning are being widely used recently for remote sensing (RS) image classification. The fixed architecture of CNN with a large number of network parameters is managed by learning through a number of iterations, and, thereby increasing the computational burden. To deal with this issue, an adaptive granulation-based CNN (AGCNN) model is proposed in the present study. AGCNN works in the framework of fuzzy set theoretic data granulation and adaptive learning by upgrading the network architecture to accommodate the information of new samples, and avoids iterative training, unlike conventional CNN. Here, granulation is done both on the 2-D input image and its 1-D representative feature vector output, as obtained after a series of convolution and pooling layers. While the class-dependent fuzzy granulation on input image space exploits more domain knowledge for uncertainty modeling, rough set theoretic reducts computed on them select only the relevant features for input to CNN. During classification of unknown patterns, a new principle of roughness-minimization with weighted membership is adopted on overlapping granules to deal with the ambiguous cases. All these together improve the classification accuracy of AGCNN, while reducing the computational time significantly. The superiority of AGCNN over some state-of-the-art models in terms of different performance metrics is demonstrated for hyperspectral and multispectral images both quantitatively and visually.

M2P2: Multimodal Persuasion Prediction Using Adaptive Fusion

Identifying persuasive speakers in an adversarial environment is a critical task. In a national election, politicians would like to have persuasive speakers campaign on their behalf. When a company faces adverse publicity, they would like to engage persuasive advocates for their position in the presence of adversaries who are critical of them. Debates represent a common platform for these forms of adversarial persuasion. This paper solves two problems: the Debate Outcome Prediction (DOP) problem predicts who wins a debate while the Intensity of Persuasion Prediction (IPP) problem predicts the change in the number of votes before and after a speaker speaks. Though DOP has been previously studied, we are the first to study IPP. Past studies on DOP fail to leverage two important aspects of multimodal data: 1) multiple modalities are often semantically aligned, and 2) different modalities may provide diverse information for prediction. Our M2P2 (Multimodal Persuasion Prediction) framework is the first to use multimodal (acoustic, visual, language) data to solve the IPP problem. To leverage the alignment of different modalities while maintaining the diversity of the cues they provide, M2P2 devises a novel adaptive fusion learning framework which fuses embeddings obtained from two modules -- an alignment module that extracts shared information between modalities and a heterogeneity module that learns the weights of different modalities with guidance from three separately trained unimodal reference models. We test M2P2 on the popular IQ2US dataset designed for DOP. We also introduce a new dataset called QPS (from Qipashuo, a popular Chinese debate TV show) for IPP - we plan to release this dataset when the paper is published. M2P2 significantly outperforms 3 recent baselines on both datasets.

Dual-Level Adaptive and Discriminative Knowledge Transfer for Cross-Domain Recognition

Unsupervised domain adaptation is an appealing technique to learn robust classifiers for unlabeled target domain by borrowing knowledge from well-established source domain. However, previous works mainly suffer from two limitations: 1) the classifier trained on labeled source data may be prone to overfitting the source distribution, lowering its performance on the target domain; 2) the adaptation process will be misled by conditional distribution matching using hard pseudo labels of target samples. This paper presents a Dual-Level Adaptive and Discriminative (DLAD) classifier learning framework, in which transfer classifier and distribution adaptation can be mutually beneficial for effective knowledge transfer. Specifically, we aim to achieve a domain-level adaptive classifier by considering structural risk minimization (SRM) on both domains and performing weighted distribution adaptation, which facilitates joint classifier learning in a semi-supervised manner. To further achieve a class-level discriminative classifier, we explicitly leverage unlabeled target data to promote classifier learning based on class probabilities, which refines the decision boundary to be more discriminative for unlabeled target data. To the best of our knowledge, DLAD is the first attempt to consider the principle of SRM on the target domain, which significantly boosts the discriminative power of transfer classifier and yields a tighter generalization bound. Experimental evaluations on several standard cross-domain datasets show that DLAD significantly outperforms other competitive methods.

A Bayesian-based knowledge tracing model for improving safety training outcomes in construction: An adaptive learning framework

Safety training plays a pivotal role in effectively reducing unsafe behaviors in the construction industry. Despite the numerous effort to improve safety training, existing studies lacked consideration of trainees' different learning characters, nor did they adapt the suitable training materials to trainees' mastery of safety knowledge. Against this contextual backdrop, this research proposes a Bayesian-based Knowledge Tracing (BKT) model to recommend personalized training materials according to trainees's learning progress. The proposed BKT model tracks and predicts trainees' performance with their cognitive characters, abilities, and historical training records. It also adjusts trainee's probability of mastering safety knowledge concepts for determining future training sessions. In this way, the safety training is adaptive and personalized, thus more effective. An exploration study is conducted in the laboratory environment to validate the effectiveness and feasibility of the proposed BKT model. The research results showed that 83.33% of the respondents felt gained safety knowledge after the training, and 66.67% of the respondents affirmed the effectiveness of the BKT model-based training system in improving the effectiveness of training. The results demonstrated that the proposed model performed well at educating safety knowledge and reducing unsafe behavior.

Memory Load and Performance-based Adaptive Smartphone E-learning Framework for E-commerce Applications in Online Learning

<p>The term e-commerce is not confined to the purchase and sale of goods only. There are several occasions where students are not able to comprehend any idea on their own. With the availability of online learning platforms such as Massive Open Online Courses (MOOCs) and Virtual Learning Environments (VLEs), students may visit online Internet sites, where various articles are made available with a single click. With mobile devices in their hands, they can also listen to the presentations of different academics from anywhere and at any time. In an online learning environment, it is challenging to provide tailored learning content to students that fulfill their needs and requirement. Therefore, we in this research paper propose an adaptive smartphone learning framework. The framework first considers students’ academic performance, preferred learning content, and memory load i.e., cognitive characteristics. Based on students’ academic performance, preferred learning content, and memory load, appropriate adaptive and motivational triggers are sent on students’ smartphones to guide and motivate them in their learning process. We have introduced ten types of adaptive triggers that in different scenarios will be presented to students to help them in remembering important learning points. Furthermore, performance-based motivational triggers in connection with adaptive triggers are also introduced. These motivational triggers are sent on students’ smartphones for giving them a suggestion, hope, appreciation, and warnings during their studies. In this study, we also show how different students’ learning scenarios are created and how our framework deals with those scenarios in students’ learning process.</p> <p> </p>

Cross-view graph matching for incomplete multi-view clustering

Multi-view clustering (MVC) focuses on adaptively partitioning data from diverse sources into the respective groups and has been widely studied under the assumption of complete data. However, real-world applications often encounter a more realistic incomplete multi-view clustering (IMVC) problem, where data samples are missing in certain views. There are two challenges in IMVC: 1) how to reduce the impact of the missing instances; 2) how to effectively extract the consistent information to cluster the multi-view data. To address the challenges, we propose an adaptive graph learning framework for IMVC, which optimizes the missing information to fit the intrinsic structure of each view and clusters the multi-view data by cross-view graph matching. The proposed method mainly consists of three steps. Firstly, owing to the outstanding performance of the intrinsic structure of data, we adapt it to complete the missing data of each view. Secondly, the connection graph of each view from a projection space is adaptively constructed wherein the data points are connected if and only if they belong to the same cluster. Thirdly, we further introduce a cross-view graph matching strategy to appropriately utilize complementary multi-views information and preserve view-specific semantic information. We develop an iterative algorithm for solving the proposed model. Numerical experiments on several standard datasets demonstrate the effectiveness of the proposed method.

State of Charge Estimation of Lithium-Ion Battery for Electric Vehicles under Extreme Operating Temperatures Based on an Adaptive Temporal Convolutional Network

The accurate estimation of state of charge (SOC) under various conditions is critical to the research and application of batteries, especially at extreme temperatures. However, few studies have examined the SOC estimation performance of estimation algorithms for several types of batteries under such conditions. In this study, a new method was derived for SOC estimation and a series of experiments were conducted covering five types of lithium-ion batteries with three kinds of cathode materials (i.e., LiFePO4, Li(Ni0.5Co0.2Mn0.3)O2, and LiCoO2), three test temperatures, and four real driving cycles to verify the proposed method. The test temperatures for battery operation ranges from −20 to 60 °C. Then, an adaptive machine learning (ML) framework based on the deep temporal convolutional network (TCN) and Coulomb counting method was proposed, and the structure of the estimation model was designed through the Taguchi method. The accuracy and generalizability of the proposed method were evaluated by calculating the estimation errors and their standard deviations (SDs), its average errors showed a decline of at least 49.66%, and its SDs showed a decline of at least 45.88% when compared to four popular ML methods. These traditional ML methods performed poor accuracy and stability at extreme temperatures (−20 and 60 °C) when compared to 25 °C, while the proposed adaptive method exhibited stable and high performances at different temperatures.

Robust cross-network node classification via constrained graph mutual information

The recent methods for cross-network node classification mainly exploit graph neural networks (GNNs) as feature extractor to learn expressive graph representations across the source and target graphs. However, GNNs are vulnerable to noisy factors, such as adversarial attacks or perturbations on the node features or graph structure, which can cause a significant negative impact on their learning performance. To this end, we propose a robust graph domain adaptive learning framework RGDAL which exploits an information-theoretic principle to filter the noisy factors for cross-network node classification. Specifically, RGDAL utilizes graph convolutional network (GCN) with constrained graph mutual information and an adversarial learning component to learn noise-resistant and domain-invariant graph representations. To overcome the difficulties of estimating the mutual information for the non independent and identically distributed (non-i.i.d.) graph structured data, we design a dynamic neighborhood sampling strategy that can discretize the graph and incorporate the graph structural information for mutual information estimation. Experimental results on two real-world graph datasets demonstrate that RGDAL shows better robustness for cross-network node classification compared with the SOTA graph adaptive learning methods.

Lifelong Adaptive Machine Learning for Sensor-Based Human Activity Recognition Using Prototypical Networks.

Continual learning (CL), also known as lifelong learning, is an emerging research topic that has been attracting increasing interest in the field of machine learning. With human activity recognition (HAR) playing a key role in enabling numerous real-world applications, an essential step towards the long-term deployment of such systems is to extend the activity model to dynamically adapt to changes in people’s everyday behavior. Current research in CL applied to the HAR domain is still under-explored with researchers exploring existing methods developed for computer vision in HAR. Moreover, analysis has so far focused on task-incremental or class-incremental learning paradigms where task boundaries are known. This impedes the applicability of such methods for real-world systems. To push this field forward, we build on recent advances in the area of continual learning and design a lifelong adaptive learning framework using Prototypical Networks, LAPNet-HAR, that processes sensor-based data streams in a task-free data-incremental fashion and mitigates catastrophic forgetting using experience replay and continual prototype adaptation. Online learning is further facilitated using contrastive loss to enforce inter-class separation. LAPNet-HAR is evaluated on five publicly available activity datasets in terms of its ability to acquire new information while preserving previous knowledge. Our extensive empirical results demonstrate the effectiveness of LAPNet-HAR in task-free CL and uncover useful insights for future challenges.

A self adaptive cognitive deep learning framework for classifying graphology features to Big five personality traits

A self adaptive cognitive deep learning framework for classifying graphology features to Big five personality traits

Comparative Analysis on History Teachers Attitudes towards Inclusive Education during Pandemic Times: A Survey of DATIS in Surakarta Senior High Schools

This article reports history teachers’ attitudes towards inclusive education during pandemic times. The main question addressed in this study is about to what extent the transition of teachers’ attitudes caused by the adaptive learning framework during pandemic times. A qualitative descriptive based on the framework of Differentiated of Attitudes towards Inclusive Education was used as a research method. The research participants were history teachers in the Surakarta area. The data were collected through an online interview. The findings of the research show that the trained-experienced history teachers tend to believe that students with special needs can get more facilities and learning support in special education, especially during the distance and online learning processes. Meanwhile, untrained-inexperienced history teachers tend to doubt that students with special needs education can gain significant improvement in regular classrooms. To a certain degree, it can be perceived as a symptom of new exclusivism during the pandemic time that can be proved by the tendency of trained-experienced history teachers to exclude students with special education needs based on their needs and lack of inclusive learning sources.

Use of dictionary learning for damage localization in complex structures

In this paper, to increase the performance of the sparse reconstruction method in real complex engineering structures an adaptive dictionary learning framework is proposed which updates the dictionary matrix, to allow improved compatibility with the complex structure. This proposed framework was developed by combining analytical modeling with training data sets and learning methods. An experimental evaluation of the proposed dictionary learning framework was performed on an anisotropic composite plate with a stiffener. In this experimental evaluation, a moving magnet was used as the artificial damage to capture the training data set, and both artificial damage in several locations and real impact damage was used for detection and location of the target damage. The obtained results confirmed the concept of the proposed dictionary learning framework for the improved health monitoring of complex structures.

An adaptive deep learning framework for day-ahead forecasting of photovoltaic power generation

Accurate forecasts of photovoltaic power generation (PVPG) are essential to optimize operations between energy supply and demand. Recently, the propagation of sensors and smart meters has produced an enormous volume of data, which supports the data-driven models for PVPG forecasting. Although emerging deep learning (DL) models, such as the long short-term memory (LSTM), based on historical data, have provided effective solutions for PVPG forecasting with great successes, these models utilize offline learning. As a result, DL models cannot take advantage of the opportunity to learn from newly-arrived data, and are unable to handle concept drift caused by installing extra PV units and unforeseen PV unit failures. Consequently, to improve day-ahead PVPG forecasting accuracy, as well as eliminate the impacts of concept drift, this paper proposes an adaptive LSTM (AD-LSTM), which is a DL framework that can not only acquire general knowledge from historical data, but also dynamically learn specific knowledge from newly-arrived data. A two-phase adaptive learning strategy (TP-ALS) is integrated into AD-LSTM, and a sliding window (SDWIN) algorithm is proposed, to detect concept drift in PV systems. Multiple datasets from PV systems are utilized to assess the feasibility and effectiveness of the proposed approaches. The developed AD-LSTM model demonstrates greater forecasting capability than the conventional offline LSTM model, particularly in the presence of concept drift. The forecasting skill of AD-LSTM can be improved up to 73.11%. Additionally, the proposed AD-LSTM model also achieves superior performance in terms of day-ahead PVPG forecasting for individual days and multiple days to other reference models in the literature.

Adaptive Contrastive Learning with Label Consistency for Source Data Free Unsupervised Domain Adaptation.

Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy issues and intellectual rights. In this paper, we discuss a more challenging and practical source-free unsupervised domain adaptation, which needs to adapt the source domain model to the target domain without the aid of source domain data. We propose label consistent contrastive learning (LCCL), an adaptive contrastive learning framework for source-free unsupervised domain adaptation, which encourages target domain samples to learn class-level discriminative features. Considering that the data in the source domain are unavailable, we introduce the memory bank to store the samples with the same pseudo label output and the samples obtained by clustering, and the trusted historical samples are involved in contrastive learning. In addition, we demonstrate that LCCL is a general framework that can be applied to unsupervised domain adaptation. Extensive experiments on digit recognition and image classification benchmark datasets demonstrate the effectiveness of the proposed method.

ARL: An adaptive reinforcement learning framework for complex question answering over knowledge base

Recently, reinforcement learning (RL)-based methods have achieved remarkable progress in both effectiveness and interpretability for complex question answering over knowledge base (KBQA). However, existing RL-based methods share a common limitation: the agent is usually misled by aimless exploration, as well as sparse and delayed rewards, leading to a large number of spurious relation paths. To address this issue, a new adaptive reinforcement learning (ARL) framework is proposed to learn a better and interpretable model for complex KBQA. First, instead of using a random walk agent, an adaptive path generator is developed with three atomic operations to sequentially generate the relation paths until the agent reaches the target entity. Second, a semantic policy network is presented with both character-level and sentence-level information to better guide the agent. Finally, a new reward function is introduced by considering both the relation paths and the target entity to alleviate sparse and delayed rewards. The empirical results on five benchmark datasets show that our model is more effective than state-of-the-art approaches. Compared with the strong baseline model SRN, the proposed model achieves performance improvements of 23.7% on MetaQA-3 using the metric Hits@1.