Top Research Papers on Learning

Compared to traditional machine learning, deep learning can learn deeper abstract data representation and understand scattered data properties. It has gained considerable attention for its extraordinary performances. However, existing deep learning algorithms perform poorly on new tasks. Meta-learning, known as learning to learn, is one of the effective techniques to overcome this issue. Meta-learning’s generalization ability to unknown tasks is improved by employing prior knowledge to assist the learning of new tasks. There are mainly three types of meta-learning methods: metric-based, model-...

A state-of-the-art survey on an intelligent robot with the capability of autonomous deciding and learning reveals that the latest research in deep learning and reinforcement learning has paved the way for highly complex tasks to be performed by robots.

Dysample, an ultra-lightweight and effective dynamic upsampler that requires no customized CUDA package and has much fewer parameters, FLOPs, GPU memory, and latency, outperforms other upsamplers across five dense prediction tasks.

This work introduces MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks.

This work presents a new paradigm for continual learning that aims to train a more succinct memory system without accessing task identity at test time, and achieves competitive results against rehearsal-based methods even without a re-hearsal buffer.

This article provides a conceptual distinction between relevant terms and concepts, explains the process of automated analytical model building through machine learning and deep learning, and discusses the challenges that arise when implementing such intelligent systems in the field of electronic markets and networked business.

The findings show LA research was conducted mainly to measure rather than to support SRL, and there is a critical need to exploit the LA support mechanisms further in order to ultimately use them to foster student SRL in online learning environments.

A novel meta-learning method to learn how to learn task-adaptive classifier–predictor to generate classifier weights for few-shot classification that can better capture characteristics of each category in a novel task and thus generate a more accurate and effective classifier.

Organisational Learning (OL) is essential for the survival of an organisation and has led to a significant amount of conceptual and empirical studies. However, no attempt has yet been made to track the overall evolution of OL literature along with the inter-related concepts of learning organisation and organisational learning orientation. Therefore, the present study attempts to fill this gap and track the interdisciplinary flow of knowledge by applying a structural methodology called Systematic Literature Network Analysis (SLNA). The results reveal four main areas of investigation within the ...

Strategies of the self-regulated learning (SRL) framework for K-12 students learning in online environments to support remote learning with online and digital tools during the COVID-19 pandemic are described.

Surprisingly, the best gossip variants perform comparably to the best federated learning variants overall, thus providing a fully decentralized alternative to federatedLearning.

A new method named adversarial domain augmentation is proposed to solve the Out-of-Distribution (OOD) generalization problem by leveraging adversarial training to create "fictitious" yet "challenging" populations, from which a model can learn to generalize with theoretical guarantees.

This work proposes an efficient method for retrieving prompts for in-context learning using annotated data and an LM, and trains an efficient dense retriever from this data, which is used to retrieve training examples as prompts at test time.

MetaLoc is the first fingerprinting-based localization framework that leverages the Model-Agnostic Meta-Learning (MAML), built on a deep neural network with strong representation capabilities, and is trained on historical data sourced from well-calibrated environments, employing a two-loop optimization mechanism to obtain the meta-parameters.

It is concluded that SRL support is beneficial for students' learning but that it should be carefully designed to avoid students’ dissatisfaction, which could potentially nullify these beneficial effects on learning.

The authors have identified new attributes and scaled-down the attributes identified earlier, which would help identify the learner's learning style, and implemented classification algorithms and compared the accuracy of the different algorithms on the dataset.

This review paper discusses personalised and adaptive learning platforms, approaches, and solutions implemented in the prevailing eLearning systems, describing personalisation with basic concepts, describing competency-based learning, customised web service solutions, and presentation approaches.

This article provides a concise but holistic review of the recent advances made in using machine learning to achieve safe decision-making under uncertainties, with a focus on unifying the language and frameworks used in control theory and reinforcement learning research.

This paper is using deep learning to uncover higher-level representational features, to clearly explain transfer learning, to provide current solutions and evaluate applications in diverse areas of transfer learning as well as deep learning.

Reinforcement learning is a learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in reinforcement learning upon the fast development of deep neural networks. Along with the promising prospects of reinforcement learning in numerous domains such as robotics and game-playing, transfer learning has arisen to tackle various challenges faced by reinforcement learning, by transferring knowledge from external expertise to facilitate the efficiency and effectiveness of the learning process. In this survey, we systematically investigate the r...

An insight survey for machine learning along with deep learning applications in various domains is provided and some applications with new normal COVID-19 blues are exemplified.

This paper aims to present a contribution to the debate on learning styles and the learning process discussing some classic learning styles theories: Kolb’s experiential learning theory and learning style model, Honey and Munford’s Learning Style Model, Felder and Silverman’s learning styles and the VARK model. We propose to link them with the learning process by exploring knowledge derived from other areas, such as Biology and the Neurosciences, to broaden the horizons of understanding on the subject. This reflection was developed as part of the ERASMUS ​+ ​research project IC-ENGLISH – Innov...

The findings suggest that multimodal learning analytics can accurately predict students?

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to avoid errors due to distributional shift. This trade-off is critical, because most current offline reinforcement learning methods need to query the value of unseen actions during training to improve the policy, and therefore need to either constrain these actions to be in-distribution, or else regularize their values. We propose an offline RL method that ne...

Conservative Q-learning (CQL) is proposed, which aims to address limitations of offline RL methods by learning a conservative Q-function such that the expected value of a policy under this Q- function lower-bounds its true value.

This review of talks and discussions in the "Deep Learning and Reinforcement Learning" session of the symposium, International Symposium on Artificial Intelligence and Brain Science, discusses whether the authors can achieve comprehensive understanding of human intelligence based on the recent advances of deep learning and reinforcement learning algorithms.

This survey systematically investigates the recent progress of transfer learning approaches in the context of deep reinforcement learning, and provides a framework for categorizing the state-of-the-art transfer Learning approaches under which to analyze their goals, methodologies, compatible reinforcement learning backbones, and practical applications.

It is concluded that ML and DL are powerful new tools for predictive modelling and data analysis, comparable to other traditional statistical tools.

This paper provides a brief historical review of collaborative learning and cooperative learning to identify the origins of each, where they diverge from each other, and where they are aligned.

A personalized variant of the well-known Federated Averaging algorithm is studied and its performance is characterized by the closeness of underlying distributions of user data, measured in terms of distribution distances such as Total Variation and 1-Wasserstein metric.

The incentive mechanism for federated learning to motivate edge nodes to contribute model training is studied and a deep reinforcement learning-based (DRL) incentive mechanism has been designed to determine the optimal pricing strategy for the parameter server and the optimal training strategies for edge nodes.

OptiPrompt is proposed, a novel and efficient method which directly optimizes in continuous embedding space and is able to predict an additional 6.4% of facts in the LAMA benchmark.

This article presents a framework for curriculum learning (CL) in reinforcement learning, and uses it to survey and classify existing CL methods in terms of their assumptions, capabilities, and goals.

Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set wit...

An overview of the extent to which e- Learning is used at higher education is presented and e-learning from the perspective of students and teachers is explored and the current condition of e- learning that utilizes interactive technology to enhance the learning experience is explained.

This study investigated the impact of a chatbot-based micro-learning system on students’ learning motivation and performance, suggesting that students are sufficiently competent to learn independently in the chat bot-based learning environment without the need for continuous face-to-face delivery.

It is proposed that technological solutions and digital tools available today and in the future will help advance the theory underlying the cognitive, metacognitive, emotional, and social components of individual, peer, and group learning when seen through a multidisciplinary lens.

Associations between assessment and learning are widely studied and often organized around the notions of Assessment as Learning (AaL), Assessment for Learning (AfL), and Assessment of Learning (AoL). Although these notions are appealing in theory, the notions are unclear constructs to comprehend, as both their definitions and their practice are used inconsistently in educational research. We present a synthesis of common characteristics among these notions, based on a scoping review on definitions and descriptions of AaL, AfL, and AoL (131 studies). The synthesis of common characteristics con...

Adaptive learning systems personalize instruction to students’ individual learning needs and abilities. Such systems have shown positive impacts on learning. Many schools in the United States have adopted adaptive learning systems, and the rate of adoption in China is accelerating, reaching almost 2 million unique users for one product alone in the past 3 years. Given such rapid adoption in China, it is useful to examine the efficacy of adaptive learning within that country’s educational system. This study aimed to compare the learning impacts of individualized adaptive learning courseware to ...

The history of machine learning development from shallow to deep learning and its applications in construction and suggestions which may benefit researchers in terms of combining specific knowledge domains in construction with machine learning algorithms so as to develop dedicated deep network models for the industry.