Search

Current mainstream for Chinese grammatical error correction methods rely on deep neural network models, which require a large amount of high-quality data for training. However, existing Chinese grammatical error correction corpora have a low annotation quality and high noise levels, leading to a low generalization ability of the models and difficulty in handling complex sentences. To address this issue, this paper proposes a dynamic assessment-based curriculum learning method for Chinese grammatical error correction. The proposed approach focuses on two key components: defining the difficulty of training samples and devising an effective training strategy. In the difficulty assessment phase, we enhance the accuracy of the curriculum sequence by dynamically updating the evaluation model. During the training strategy phase, a multi-stage dynamic progressive approach is employed to select training samples of varying difficulty levels, which helps prevent the model from prematurely converging to local optima and enhances the overall training effectiveness. Experimental results on the MuCGEC and NLPCC 2018 Chinese grammatical error correction datasets show that the proposed curriculum learning method significantly improves the model's error correction performance, with F0.5 scores increasing by 0.9 and 1.05, respectively, validating the method's effectiveness. [ABSTRACT FROM AUTHOR]

Robotic systems are crucial in modern manufacturing. Complex assembly tasks require the collaboration of multiple robots. Their orchestration is challenging due to tight tolerances and precision requirements. In this work, we set up two Franka Panda robots performing a peg-in-hole insertion task of 1 mm clearance. We structure the control system hierarchically, planning the robots' feedback-based trajectories with a central policy trained with reinforcement learning. These trajectories are executed by a low-level impedance controller on each robot. To enhance training convergence, we use reverse curriculum learning, novel for such a two-armed control task, iteratively structured with a minimum requirements and fine-tuning phase. We incorporate domain randomization, varying initial joint configurations of the task for generalization of the applicability. After training, we test the system in a simulation, discovering the impact of curriculum parameters on the emerging process time and its variance. Finally, we transfer the trained model to the real-world, resulting in a small decrease in task duration. Comparing our approach to classical path planning and control shows a decrease in process time, but higher robustness towards calibration errors. [ABSTRACT FROM AUTHOR]

Continual learning (CL) is one of the most promising trends in recent machine learning research. Its goal is to go beyond classical assumptions in machine learning and develop models and learning strategies that present high robustness in dynamic environments. This goal is realized by designing strategies that simultaneously foster the incorporation of new knowledge while avoiding forgetting past knowledge. The landscape of CL research is fragmented into several learning evaluation protocols, comprising different learning tasks, datasets, and evaluation metrics. Additionally, the benchmarks adopted so far are still distant from the complexity of real-world scenarios, and are usually tailored to highlight capabilities specific to certain strategies. In such a landscape, it is hard to clearly and objectively assess models and strategies. In this work, we fill this gap for CL on image data by introducing two novel CL benchmarks that involve multiple heterogeneous tasks from six image datasets, with varying levels of complexity and quality. Our aim is to fairly evaluate current state-of-the-art CL strategies on a common ground that is closer to complex real-world scenarios. We additionally structure our benchmarks so that tasks are presented in increasing and decreasing order of complexity—according to a curriculum—in order to evaluate if current CL models are able to exploit structure across tasks. We devote particular emphasis to providing the CL community with a rigorous and reproducible evaluation protocol for measuring the ability of a model to generalize and not to forget while learning. Furthermore, we provide an extensive experimental evaluation showing that popular CL strategies, when challenged with our proposed benchmarks, yield sub-par performance, high levels of forgetting, and present a limited ability to effectively leverage curriculum task ordering. We believe that these results highlight the need for rigorous comparisons in future CL works as well as pave the way to design new CL strategies that are able to deal with more complex scenarios. [ABSTRACT FROM AUTHOR]

Bayesian networks (BNs) are highly effective in handling uncertain problems, which can assist in decision-making by reasoning with limited and incomplete information. Learning a faithful directed acyclic graph (DAG) from a large number of complex samples of a joint distribution is currently a challenging combinatorial problem. Due to the growing volume and complexity of data, some Bayesian structure learning algorithms are ineffective and lack the necessary precision to meet the required needs. In this paper, we propose a new PCCL-CC algorithm. To ensure the accuracy of the network structure, we introduce the new ensemble weights and edge constraints setting mechanism. In this mechanism, we employ a method that estimates the interaction between network nodes from multiple perspectives and divides the learning process into multiple stages. We utilize an asymmetric weighted ensemble method and adaptively adjust the network structure. Additionally, we propose a causal discovery method that effectively utilizes the causal relationships among data samples to correct the network structure and mitigate the influence of Markov equivalence classes (MEC). Experimental results on real datasets demonstrate that our approach outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Physics-informed neural networks (PINNs) encode prior physical knowledge into neural networks, alleviating the need for extensive data volume within the network. However, for long-term problems involving time-dependent partial differential equations, the traditional PINN exhibits poor stability and struggles to obtain effective solutions. To address this challenge, a novel physics-informed neural network based on curriculum learning and transfer learning (CTL-PINN) was introduced. The main idea of this method is to transform the problem of long-term course simulation into multiple short-term course simulation problems within this time domain. Under the concept of curriculum learning, and step by step from simpleness to difficulty, the scope of the time domain to be solved was gradually expanded by training the PINN within small time quanta. Furthermore, the transfer learning method was adopted to transfer across the time domain based on the curriculum learning, and the PINN was gradually employed for solution, thus to achieve long-term simulation of convection-diffusion behaviors on curved surfaces. The CTL-PINN was combined with the extrinsic surface operator processing technology to simulate long-term convection-diffusion behaviors on complex surfaces, and the effectiveness and robustness of the improved physics-informed neural network were verified through multiple numerical examples. [ABSTRACT FROM AUTHOR]

Causal structure learning plays a crucial role in the current field of artificial intelligence, yet existing causal structure learning methods are susceptible to interference from data sample noise and often become trapped in local optima. To address these challenges, this paper introduces a continuous optimization algorithm based on the curriculum learning framework: CL-NOTEARS. The model utilizes the curriculum loss function during training as a priority evaluation metric for curriculum selection and formulates the sample learning sequence of the model through task-level curricula, thereby enhancing the model's learning performance. A curriculum-based sample prioritization strategy is employed that dynamically adjusts the training sequence based on variations in loss function values across different samples throughout the training process. The results demonstrate a significant reduction in the impact of sample noise in the data, leading to improved model training performance. [ABSTRACT FROM AUTHOR]

Over the last few years Literature-based Discovery (LBD) has regained popularity as a means to enhance the scientific research process. The resurgent interest has spurred the development of supervised and semi-supervised machine learning models aimed at making previously implicit connections between scientific concepts/entities within often extensive bodies of literature explicit—i.e., suggesting novel scientific hypotheses. In doing so, understanding the temporally evolving interactions between these entities can provide valuable information for predicting the future development of entity relationships. However, existing methods often underutilize the latent information embedded in the temporal aspects of the interaction data. Motivated by applications in the food domain—where we aim to connect nutritional information with health-related benefits—we address the hypothesis-generation problem using a temporal graph-based approach. Given that hypothesis generation involves predicting future (i.e., still to be discovered) entity connections, in our view the ability to capture the dynamic evolution of connections over time is pivotal for a robust model. To address this, we introduce THiGER, a novel batch contrastive temporal node-pair embedding method. THiGER excels in providing a more expressive node-pair encoding by effectively harnessing node-pair relationships. Furthermore, we present THiGER-A, an incremental training approach that incorporates an active curriculum learning strategy to mitigate label bias arising from unobserved connections. By progressively training on increasingly challenging and high-utility samples, our approach significantly enhances the performance of the embedding model. Empirical validation of our proposed method demonstrates its effectiveness on established temporal-graph benchmark datasets, as well as on real-world datasets within the food domain. [ABSTRACT FROM AUTHOR]

Stylized neural machine translation (NMT) aims to translate sentences of one style into sentences of another style, it is essential for the application of machine translation in a real-world scenario. Most existing methods employ an encoder-decoder structure to understand, translate, and transform style simultaneously, which increases the learning difficulty of the model and leads to poor generalization ability. To address these issues, we propose a curriculum pre-training framework to improve stylized NMT. Specifically, we design four pre-training tasks of increasing difficulty to assist the model to extract more features essential for stylized translation. Then, we further propose a stylized-token aligned data augmentation method to expand the scale of pre-training corpus for alleviating the data-scarcity problem. Experiments show that our method achieves competitive results on MTFC and Modern-Classical translation dataset. [ABSTRACT FROM AUTHOR]

Generative document summarization is a natural language processing technique that generates short summary sentences while preserving the content of long texts. Various fine-tuned pre-trained document summarization models have been proposed using a specific single text-summarization dataset. However, each text-summarization dataset usually specializes in a particular downstream task. Therefore, it is difficult to treat all cases involving multiple domains using a single dataset. Accordingly, when a generative document summarization model is fine-tuned to a specific dataset, it performs well, whereas the performance is degraded by up to 45% for datasets that are not used during learning. In short, summarization models perform well with in-domain cases, as the dataset domain during training and evaluation is the same but perform poorly with out-domain inputs. In this paper, we propose a new curriculum-learning method using mixed datasets while training a generative summarization model to be more robust on out-domain datasets. Our method performed better than XSum with 10%, 20%, and 10% lower performance degradation in CNN/DM, which comprised one of two test datasets used, compared to baseline model performance. [ABSTRACT FROM AUTHOR]

Temporal knowledge graph representation approaches encounter significant challenges in handling the complex dynamic relations among entities, relations, and time. These challenges include the high difficulty of training and poor generalization performance, particularly with large datasets. To address these issues, this paper introduces curriculum learning strategies from machine learning, aiming to improve learning efficiency through effective curriculum planning. The proposed framework constructs a high-dimensional filtering model based on graph-based high-order receptive fields and employs a scoring model that uses a curriculum temperature strategy to evaluate the difficulty of temporal knowledge graph data quadruples at each stage. By progressively expanding the receptive field and dynamically adjusting the difficulty of learning samples, the model can better understand and capture multi-level information within the graph structure, thereby improving its generalization capabilities. Additionally, a temperature factor is introduced during model training to optimize parameter gradients, alongside a gradually increasing training strategy to reduce training difficulty. Experiments on the benchmark datasets ICEWS14 and ICEWS05-15 demonstrate that this framework not only significantly enhances model performance on these datasets but also substantially reduces training convergence time. [ABSTRACT FROM AUTHOR]

Aiming at the problem of online route planning for aircraft, an online autonomous decision-making method for aircraft based on deep reinforcement learning (DRL) is proposed. Firstly, the maneuvering model and detection model of the aircraft are explained, and then the deep deterministic policy gradient (DDPG) algorithm of DRL is employed to construct the frame of the aircraft policy model. On this basis, a curriculum learning (CL)-DDPG algorithm based on CL is proposed, which decomposes the online route planning task, guides the aircraft to learn the strategies of target approach, threat avoidance, and air route optimization. The corresponding Gausdan noises are set to help the aircraft explore and optimize the strategy. And, the adaptive learning and decision-making control of the aircraft in complex scenarios are realized. Simulation experiments show that the CL-DDPG algorithm can effectively improve the training efficiency of the model. The algorithm model has higher task success rate, excellent generalization and robustness, and can be better applied to online route planning tasks in complex dynamic environments. [ABSTRACT FROM AUTHOR]

Reinforcement learning, a cornerstone in the expansive landscape of artificial intelligence, has asserted its dominance as the prevailing methodology in contemporary multiagent system decision-making because of its formidable efficacy. However, the path to the zenith of algorithmic excellence is fraught with challenges intrinsic to traditional multiagent reinforcement learning algorithms, such as dimensionality explosion, scarcity of training samples, and the labyrinthine nature of migration processes. In a concerted effort to surmount these formidable challenges and propel the evolution of algorithmic prowess, this paper unfurls its inquiry from the perspective of learning mechanisms and undertakes an exhaustive exploration of the symbiotic integration of learning mechanisms and reinforcement learning. At the inception of this scholarly expedition, we meticulously delineate the rudimentary principles underpinning multiagent algorithms, present a historical trajectory tracing their developmental evolution, and cast a discerning eye upon the salient challenges that have been formidable impediments in their trajectory. The ensuing narrative charts a course into the avant-garde realm of multiagent reinforcement learning methods anchored in learning mechanisms, a paradigmatic shift that emerges as an innovative frontier in the field. Among these learning mechanisms, meta-learning and transfer learning are empirically validated as useful instruments in hastening the learning trajectory of multiagent systems and simultaneously mitigating the intricate challenges posed by dimensionality explosion. This paper assumes the role of a sagacious guide through the labyrinthine landscape of multiagent reinforcement learning, focusing on the manifold applications of learning mechanisms across diverse domains. A comprehensive review delineates the impact of learning mechanisms in curriculum learning, evolutionary games, meta-learning, hierarchical learning, and transfer learning. The research outcomes within these thematic realms are methodically cataloged, with a discerning eye cast upon the limitations inherent in each methodology and erudite propositions for the trajectory of future improvements. The discourse pivots toward synthesizing advancements and accomplishments wrought by fusion algorithms in practical milieus. This paper meticulously examines the transformative impact of fusion algorithms in real-world applications, with a detailed exposition of their deployment in domains as diverse as traffic control and gaming. Simultaneously, an incisive analysis charting the future trajectory of fusion algorithms is conducted. This prediction encompasses exploring nascent theories, refining algorithmic efficacy, and expanding dissemination and application across a broader spectrum of domains. Through this scholarly odyssey, this paper provides an invaluable compass for navigating the uncharted waters of future research endeavors and the judicious deployment of multiagent reinforcement learning algorithms in pragmatic scenarios.

Abstract Bayesian networks (BNs) are highly effective in handling uncertain problems, which can assist in decision-making by reasoning with limited and incomplete information. Learning a faithful directed acyclic graph (DAG) from a large number of complex samples of a joint distribution is currently a challenging combinatorial problem. Due to the growing volume and complexity of data, some Bayesian structure learning algorithms are ineffective and lack the necessary precision to meet the required needs. In this paper, we propose a new PCCL-CC algorithm. To ensure the accuracy of the network structure, we introduce the new ensemble weights and edge constraints setting mechanism. In this mechanism, we employ a method that estimates the interaction between network nodes from multiple perspectives and divides the learning process into multiple stages. We utilize an asymmetric weighted ensemble method and adaptively adjust the network structure. Additionally, we propose a causal discovery method that effectively utilizes the causal relationships among data samples to correct the network structure and mitigate the influence of Markov equivalence classes (MEC). Experimental results on real datasets demonstrate that our approach outperforms state-of-the-art methods.

Abstract This work addresses a critical issue: the deterioration of concrete structures due to fine-grained cracks, which compromises their strength and longevity. To tackle this problem, experts have turned to computer vision (CV) based automated strategies, incorporating object detection and image segmentation techniques. Recent efforts have integrated complex techniques such as deep convolutional neural networks (DCNNs) and transformers for this task. However, these techniques encounter challenges in localizing fine-grained cracks. This paper presents a self-supervised 'you only look once' (SS-YOLO) approach that utilizes a YOLOv8 model. The novel methodology amalgamates different attention approaches and pseudo-labeling techniques, effectively addressing challenges in fine-grained crack detection and segmentation in concrete structures. It utilizes convolution block attention (CBAM) and Gaussian adaptive weight distribution multi-head self-attention (GAWD-MHSA) modules to accurately identify and segment fine-grained cracks in concrete buildings. Additionally, the assimilation of curriculum learning-based self-supervised pseudo-labeling (CL-SSPL) enhances the model's ability when applied to limited-size data. The efficacy and viability of the proposed approach are demonstrated through experimentation, results, and ablation analysis. Experimental results indicate a mean average precision (mAP) of at least 90.01%, an F1 score of 87%, and an intersection over union threshold greater than 85%. It is evident from the results that the proposed method yielded at least 2.62% and 4.40% improvement in mAP and F1 values, respectively, when tested on three diverse datasets. Moreover, the inference time taken per image is 2 ms less than that of the compared methods.

On the one hand, the existing knowledge graph entity prediction methods only use the neighborhood and graph structure information to enhance the node information, and ignore the multi-modal information outside the knowledge graph to enhance the knowledge graph information. On the other hand, when comparing positive and negative samples to train the model, the negative sample random ordering results in poor training effect, and there is no additional information to help the training process of negative samples. Therefore, a multi-modal curriculum learning knowledge graph entity prediction model (MMCL) is proposed. Firstly, multi-modal information is introduced into the knowledge graph to achieve information enhancement, and the multi-modal information fusion process is optimized using generative adversarial network (GAN). The samples generated by the generator enhance the knowledge graph information, and at the same time improve the discriminator??s ability to distinguish the truth and falsity of triples. Secondly, the course learning algorithm is used to sort the negative samples from easy to difficult according to the difficulty of the negative samples. By adding the sorted negative samples into the training process hierarchically through the pace function, it is more beneficial to playing the effect of negative samples in identifying the truth and falseness of triples, and at the same time, no label learning avoids the false-negative problem in the late training period. The discriminators share parameters with course learning training models to help improve the training effect of negative samples. Experiments are conducted on two datasets, FB15k-237 and WN18RR. The results show that compared with the baseline model, MMCL is significantly improved in mean reciprocal rank (MRR), Hits@1, Hits@3 and Hits@10. The validity and feasibility of the proposed model are verified.

In recent years, the sample mining strategy has been integrated into the loss function of face recognition, significantly improving the performance of face recognition. But most of the work focuses on how to mine difficult samples during the training phase, without considering the potential unrecognized sample images in the difficult samples, resulting in poor recognition performance of the model for low-quality facial images. To solve this problem, this paper proposes a hybrid adaptive loss function MixFace that combines sample difficulty adaptation and image quality adaptation. The loss function combines the CurricularFace based on curriculum learning with the image adaptive loss function AdaFace. The feature norm is incorporated into the loss function as an image quality indicator. On the premise of focusing on image quality, this paper focuses on simple samples in the early training stage and difficult samples in the later training stage, reducing the network model’s attention to some low-quality unrecognized samples in difficult samples. Trained on CASIA-WebFace and MS1MV2 datasets, MixFace shows varying degrees of performance improvement compared with CurricularFace and AdaFace on high-quality test sets LFW, CFP_FP, AgeDB, CALFW, and CPLFW. At the same time, MixFace shows better recognition performance than CurricularFace and AdaFace on medium quality test sets IJB-B, IJB-C and low-quality test set TinyFace. Experimental results show that MixFace can effectively reduce the interference of unrecognized images, thereby improving the performance of low-quality face recognition. At the same time, benefiting from the curriculum learning method in MixFace, it can still maintain good performance for high-quality face recognition.

Scene text detection has been widely studied on haze‐free images with reliable ground truth annotation. However, detecting scene text in inclement weather conditions remains a major challenge due to the severe domain distribution mismatch problem. This paper introduces a domain adaptation curriculum learning method to address this problem. The scene text detector is self‐trained in an easy‐to‐hard manner using the pseudo‐labels predicted from foggy images. Thus, our method reduces the pseudo‐labeling noise level. Then, a feature alignment module is introduced to help the network learn domain‐invariant features by training a domain classifier. Experimental results show that our method improved significantly on both synthetic foggy data sets and natural foggy data sets, outperforming many state‐of‐the‐art scene text detectors. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Face recognition for surveillance remains a complex challenge due to the disparity between low-resolution (LR) face images captured by surveillance cameras and the typically high-resolution (HR) face images in databases. To address this cross-resolution face recognition problem, we propose a two-stage dual-resolution face network to learn more robust resolution-invariant representations. In the first stage, we pre-train the proposed dual-resolution face network using solely HR images. Our network utilizes a two-branch structure and introduces bilateral connections to fuse the high- and low-resolution features extracted by two branches, respectively. In the second stage, we introduce the triplet loss as the fine-tuning loss function and design a training strategy that combines the triplet loss with competence-based curriculum learning. According to the competence function, the pre-trained model can train first from easy sample sets and gradually progress to more challenging ones. Our method achieves a remarkable face verification accuracy of 99.25% on the native cross-quality dataset SCFace and 99.71% on the high-quality dataset LFW. Moreover, our method also enhances the face verification accuracy on the native low-quality dataset. [ABSTRACT FROM AUTHOR]

Collaborative edge intelligence, a distributed computing paradigm, refers to a system where multiple edge devices work together to process data and perform distributed machine learning (DML) tasks locally. Decentralized Internet of Things (IoT) devices share knowledge and resources to improve the quality of service (QoS) of the system with reduced reliance on centralized cloud infrastructure. However, the paradigm is vulnerable to free-riding attacks, where some devices benefit from the collective intelligence without contributing their fair share, potentially disincentivizing collaboration and undermining the system's effectiveness. Moreover, data collected from heterogeneous IoT devices may contain biased information that decreases the prediction accuracy of DML models. To address these challenges, we propose a novel incentive mechanism that relies on time-dependent blockchain records and multi-access edge computing (MEC). We formulate the QoS problem as an unbounded multiple knapsack problem at the network edge. Furthermore, a decentralized valuation protocol is introduced atop blockchain to incentivize contributors and disincentivize free-riders. To improve model prediction accuracy within latency requirements, a data scheduling algorithm is given based on a curriculum learning framework. Based on our computer simulations using heterogeneous datasets, we identify two critical factors for enhancing the QoS in collaborative edge intelligence systems: (1) mitigating the impact of information loss and free-riders via decentralized data valuation and (2) optimizing the marginal utility of individual data samples by adaptive data scheduling. [ABSTRACT FROM AUTHOR]

Background: Pneumothorax detection is often challenging, particularly when radiographic features are subtle. This study introduces a deep learning model that integrates curriculum learning and ChatGPT to enhance the detection of pneumothorax in chest X-rays. Methods: The model training began with large, easily detectable pneumothoraces, gradually incorporating smaller, more complex cases to prevent performance plateauing. The training dataset comprised 6445 anonymized radiographs, validated across multiple sites, and further tested for generalizability in diverse clinical subgroups. Performance metrics were analyzed using descriptive statistics. Results: The model achieved a sensitivity of 0.97 and a specificity of 0.97, with an area under the curve (AUC) of 0.98, demonstrating a performance comparable to that of many FDA-approved devices. Conclusions: This study suggests that a structured approach to training deep learning models, through curriculum learning and enhanced data extraction via natural language processing, can facilitate and improve the training of AI models for pneumothorax detection. [ABSTRACT FROM AUTHOR]

This paper introduces a novel approach for extending the applicability of pre-trained models to accommodate longer texts. Addressing the inherent limitation of quadratic performance in attention models within transformers, we propose the concept of fused transformers. By integrating new adaptor techniques, we enhance the encoding of lengthy text segments by breaking them into shorter spans. Subsequently, these segments are fused to increase the model's effectiveness in processing extended texts. This fusion mechanism serves to fortify the model's capacity for fine-tuning. Furthermore, we implement a length-based curriculum for expedited training Our experiments yielded 16 Rouge-2 points, representing a doubling of the score achieved by the vanilla fine-tuning method on the newly introduced "Mukhtasar" dataset for summarization. This highlights the effectiveness of managing complex relations among text segments and confirms that our method can outperform conventional training approaches. [ABSTRACT FROM AUTHOR]

This work addresses a critical issue: the deterioration of concrete structures due to fine-grained cracks, which compromises their strength and longevity. To tackle this problem, experts have turned to computer vision (CV) based automated strategies, incorporating object detection and image segmentation techniques. Recent efforts have integrated complex techniques such as deep convolutional neural networks (DCNNs) and transformers for this task. However, these techniques encounter challenges in localizing fine-grained cracks. This paper presents a self-supervised 'you only look once' (SS-YOLO) approach that utilizes a YOLOv8 model. The novel methodology amalgamates different attention approaches and pseudo-labeling techniques, effectively addressing challenges in fine-grained crack detection and segmentation in concrete structures. It utilizes convolution block attention (CBAM) and Gaussian adaptive weight distribution multi-head self-attention (GAWD-MHSA) modules to accurately identify and segment fine-grained cracks in concrete buildings. Additionally, the assimilation of curriculum learning-based self-supervised pseudo-labeling (CL-SSPL) enhances the model's ability when applied to limited-size data. The efficacy and viability of the proposed approach are demonstrated through experimentation, results, and ablation analysis. Experimental results indicate a mean average precision (mAP) of at least 90.01%, an F1 score of 87%, and an intersection over union threshold greater than 85%. It is evident from the results that the proposed method yielded at least 2.62% and 4.40% improvement in mAP and F1 values, respectively, when tested on three diverse datasets. Moreover, the inference time taken per image is 2 ms less than that of the compared methods. [ABSTRACT FROM AUTHOR]

This paper proposes a method for finding the shortest path of a mobile robot using deep reinforcement learning with utilizing Proximal policy optimization algorithm (PPO) enhanced with curriculum learning. By modelling the environment in 3D space using the Webots simulator, we extend the PPO algorithm's capabilities to handle continuous states from 8 IR sensors and control the velocities of two motors of E-puck robot. Our study uniquely integrates curriculum learning into the PPO framework, aiming to improve adaptability and training efficiency in complex environments. A comparative analysis is conducted between the modified PPO, the original PPO, and the deep deterministic policy gradient algorithm, highlighting the strengths of our approach The results demonstrate that our curriculum-augmented PPO algorithm not only accelerates the training process but also shows superior adaptability and generalization in new environments. This work underscores the significant potential of curriculum learning in enhancing the performance of deep reinforcement learning algorithms for robust and efficient robotic navigation. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As an important part of the text-to-speech (TTS) system, vocoders convert acoustic features into speech waveforms. The difference in vocoders is key to producing different types of forged speech in the TTS system. With the rapid development of general adversarial networks (GANs), an increasing number of GAN vocoders have been proposed. Detectors often encounter vocoders of unknown types, which leads to a decline in the generalization performance of models. However, existing studies lack research on detection generalization based on GAN vocoders. To solve this problem, this study proposes vocoder detection of spoofed speech based on GAN fingerprints and domain generalization. The framework can widen the distance between real speech and forged speech in feature space, improving the detection model's performance. Specifically, we utilize a fingerprint extractor based on an autoencoder to extract GAN fingerprints from vocoders. We then weight them to the forged speech for subsequent classification to learn the forged speech features with high differentiation. Subsequently, domain generalization is used to further improve the generalization ability of the model for unseen forgery types. We achieve domain generalization using domain-adversarial learning and asymmetric triplet loss to learn a better generalized feature space in which real speech is compact and forged speech synthesized by different vocoders is dispersed. Finally, to optimize the training process, curriculum learning is used to dynamically adjust the contributions of the samples with different difficulties in the training process. Experimental results show that the proposed method achieves the most advanced detection results among four GAN vocoders. The code is available at https://github.com/multimedia-infomation-security/GAN-Vocoder-detection. [ABSTRACT FROM AUTHOR]

Rhetoric is abundant and universal across different human languages. In this paper, we propose a novel curriculum learning integrated with meta-learning (CLML) model to address the task of general rhetorical identification. Specifically, we first leverage inter-category similarities to construct a dataset with curriculum characteristics for facilitating more natural easy-to-difficult learning process. Then we imitate human cognitive thinking that uses the query set in meta-learning to guide inductive network for inducing accurate class-level representations which are further improved by leveraging external class label knowledge into TapNet to construct a mapping function. Extensive experimental results demonstrate that our proposed model outperforms existing state-of-the-art models across four datasets consistently. [ABSTRACT FROM AUTHOR]

Seagrass ecosystems are pivotal in marine environments, serving as crucial habitats for diverse marine species and contributing significantly to carbon sequestration. Accurate classification of seagrass species from underwater images is imperative for monitoring and preserving these ecosystems. This paper introduces Unsupervised Curriculum Learning (UCL) to seagrass classification using the DeepSeagrass dataset. UCL progressively learns from simpler to more complex examples, enhancing the model's ability to discern seagrass features in a curriculum-driven manner. Experiments employing state-of-the-art deep learning architectures, convolutional neural networks (CNNs), show that UCL achieved overall 90.12 % precision and 89 % recall, which significantly improves classification accuracy and robustness, outperforming some traditional supervised learning approaches like SimCLR, and unsupervised approaches like Zero-shot CLIP. The methodology of UCL involves four main steps: high-dimensional feature extraction, pseudo-label generation through clustering, reliable sample selection, and fine-tuning the model. The iterative UCL framework refines CNN's learning of underwater images, demonstrating superior accuracy, generalization, and adaptability to unseen seagrass and background samples of undersea images. The findings presented in this paper contribute to the advancement of seagrass classification techniques, providing valuable insights into the conservation and management of marine ecosystems. The code and dataset are made publicly available and can be assessed here: https://github.com/nabid69/Unsupervised-Curriculum-Learning—UCL.

Following the advancement of the internet, social media gradually replaced the traditional media; consequently, the overwhelming and ever-growing process of fake news generation and propagation has now become a widespread concern. It is undoubtedly necessary to detect such news; however, there are certain challenges such as events, verification and datasets, and reference datasets related to this area face various issues such as the lack of sufficient information about news samples, the absence of subject diversity, etc. To mitigate these issues, this paper proposes a two-phase model using natural language processing and machine learning algorithms. In the first phase, two new structural features, along with other key features are extracted from news samples. In the second phase, a hybrid method based on curriculum strategy, consisting of statistical data, and a k -nearest neighbor algorithm is introduced to improve the performance of deep learning models. The obtained results indicated the higher performance of the proposed model in detecting fake news, compared to benchmark models. [ABSTRACT FROM AUTHOR]

Summary: In this paper, we propose a deep reinforcement‐based approach to generate an animation of an agent using a broom‐like tool to transport a target object. The tool is attached to the agent. So when the agent moves, the tool moves as well.The challenge is to control the agent to move and use the tool to push the target while avoiding obstacles. We propose a direction sensor to guide the agent's movement direction in environments with static obstacles. Furthermore, different rewards and a curriculum learning are implemented to make the agent efficiently learn skills for manipulating the tool. Experimental results show that the agent can naturally control the tool with different shapes to transport target objects. The result of ablation tests revealed the impacts of the rewards and some state components. [ABSTRACT FROM AUTHOR]

Brain computed tomography (CT) report generation, which aims at generating accurate and descriptive reports for Brain CT imaging, has gained growing attention from researchers. Existing works mainly train a language-generation model with complex image-text pairs for supervision, which still struggled with the following challenges: 1) the serious long-tail distribution of textual supervise signals led by imbalanced text length distribution, and 2) the insufficient medical data caused by expensive expert intervention. In this paper, we propose a novel Gaussian heuristic curriculum learning (GHCL) model to effectively tackle the long-tail data distribution and optimally utilize the limited training data. Specifically, our training process mimics the learning process of physicians in a step-wise paradigm. Firstly, we evaluate the scores of training difficulty for each sample through two elaborately designed Gaussian heuristic metrics. Then, during the training of the language-generation model, we iteratively select the most suitable batch of training samples, which is comprehensively considered by the calculated scores of training difficulty. In this way, GHCL can effectively guide the progressive learning of the report generation model and boost the quality of generated Brain CT reports. We comprehensively compare the method with previous state-of-the-art models on the Brain CT report generation dataset BCT-CHR. Experimental results demonstrate that our method surpasses previous state-of-the-art approaches and GHCL is flexible to combine with existing approaches to further improve the performance. [ABSTRACT FROM AUTHOR]

Deep reinforcement algorithms that combine reinforcement learning and deep learning approaches are used in challenging autonomous vehicle tasks. Passing the vehicle in front is one of the most challenging autonomous vehicle tasks due to the different types of subtasks involved. Recent studies in the literature use the curriculum learning approach with deep reinforcement learning to solve challenging tasks. In this study, 12 models, half of which have undergone a curriculum learning approach, are trained in a uniquely constructed environment with commonly used deep Q-networks, advantage actor critic and proximal policy optimization algorithms. The evaluation of the models is based on both the training process and the testing of the models in the environment. In the study, successful models were trained with deep Q-networks and proximal policy optimization methods, although not for all models. Among the successful models, the performance of a deep Q-network model was improved with curriculum learning, showing the positive impact of the approach. [ABSTRACT FROM AUTHOR]

Artificial Intelligence bots are extensively used in multiplayer First-Person Shooter (FPS) games. By using Machine Learning techniques, we can improve their performance and bring them to human skill levels. In this work, we focused on comparing and combining two Reinforcement Learning training architectures, Curriculum Learning and Behaviour Cloning, applied to an FPS developed in the Unity Engine. We have created four teams of three agents each: one team for Curriculum Learning, one for Behaviour Cloning, and another two for two different methods of combining Curriculum Learning and Behaviour Cloning. After completing the training, each agent was matched to battle against another agent of a different team until each pairing had five wins or ten time-outs. In the end, results showed that the agents trained with Curriculum Learning achieved better performance than the ones trained with Behaviour Cloning by a matter of 23.67% more average victories in one case. In terms of the combination attempts, not only did the agents trained with both devised methods had problems during training, but they also achieved insufficient results in the battle, with an average of 0 wins. [ABSTRACT FROM AUTHOR]

Semi-supervised node classification is a crucial challenge in relational data mining and has attracted increasing interest in research on graph neural networks (GNNs). However, previous approaches merely utilize labeled nodes to supervise the overall optimization, but fail to sufficiently explore the information of their underlying label distribution. Even worse, they often overlook the robustness of models, which may cause instability of network outputs to random perturbations. To address the aforementioned shortcomings, we develop a novel framework termed Hybrid Curriculum Pseudo-Labeling (HCPL) for efficient semi-supervised node classification. Technically, HCPL iteratively annotates unlabeled nodes by training a GNN model on the labeled samples and any previously pseudo-labeled samples, and repeatedly conducts this process. To improve the model robustness, we introduce a hybrid pseudo-labeling strategy that incorporates both prediction confidence and uncertainty under random perturbations, therefore mitigating the influence of erroneous pseudo-labels. Finally, we leverage the idea of curriculum learning to start from annotating easy samples, and gradually explore hard samples as the iteration grows. Extensive experiments on a number of benchmarks demonstrate that our HCPL beats various state-of-the-art baselines in diverse settings. [ABSTRACT FROM AUTHOR]

Curriculum Learning (CL) is an effective technique to train machine learning models where the training samples are supplied to the model in an easy-to-hard manner. Similar to human learning, the model can benefit if the data is given in a relevant order. Based on this notion, we propose to apply the concept of CL to the task of session-based recommender systems. Recurrent Neural Networks and transformer-based models have been successfully utilized for this task and shown to be very effective. In these approaches, all training examples are supplied to the model in every iteration and treated equally. However, the difficulty of a training example can vary greatly and the recommendation model can learn better if the data is given according to an easy-to-difficult curriculum. We design various curriculum strategies and show that applying the proposed CL techniques to a given recommendation model helps to improve performance.

Abstract Background Oral potentially malignant disorders (OPMDs) are associated with an increased risk of cancer of the oral cavity including the tongue. The early detection of oral cavity cancers and OPMDs is critical for reducing cancer-specific morbidity and mortality. Recently, there have been studies to apply the rapidly advancing technology of deep learning for diagnosing oral cavity cancer and OPMDs. However, several challenging issues such as class imbalance must be resolved to effectively train a deep learning model for medical imaging classification tasks. The aim of this study is to evaluate a new technique of artificial intelligence to improve the classification performance in an imbalanced tongue lesion dataset. Methods A total of 1,810 tongue images were used for the classification. The class-imbalanced dataset consisted of 372 instances of cancer, 141 instances of OPMDs, and 1,297 instances of noncancerous lesions. The EfficientNet model was used as the feature extraction model for classification. Mosaic data augmentation, soft labeling, and curriculum learning (CL) were employed to improve the classification performance of the convolutional neural network. Results Utilizing a mosaic-augmented dataset in conjunction with CL, the final model achieved an accuracy rate of 0.9444, surpassing conventional oversampling and weight balancing methods. The relative precision improvement rate for the minority class OPMD was 21.2%, while the relative $${F}_{1}$$ F 1 score improvement rate of OPMD was 4.9%. Conclusions The present study demonstrates that the integration of mosaic-based soft labeling and curriculum learning improves the classification performance of tongue lesions compared to previous methods, establishing a foundation for future research on effectively learning from imbalanced data.

The order of training samples can have a significant impact on a model’s performance. Curriculum learning is an approach for gradually training a model by ordering samples from ‘easy’ to ‘hard’. This paper proposes the novel idea of a curriculum learning strategy called Data Distribution-based Curriculum Learning (DDCL). DDCL uses the inherent data distribution of a dataset to build a curriculum based on the order of samples. Our proposed approach is innovative as it incorporates two distinct scoring methods known as DDCL-Density and DDCL-Point to determine the order of training samples. The DDCL-Density method assigns scores based on the density of samples favoring denser regions that can make initial learning easier. Conversely, DDCL-Point utilizes the Euclidean distance from the centroid of the dataset as a reference point to score samples providing an alternative perspective on sample difficulty. We evaluate the proposed DDCL approach by conducting experiments across various classifiers using a diverse set of small to medium-sized medical datasets. Results show that DDCL improves the classification accuracy, achieving increases ranging from 2% to 10% compared to baseline methods and other state-of-the-art techniques. Moreover, analysis of the error losses for a single training epoch reveals that DDCL not only improves accuracy but also increases the convergence rate, underlining its potential for more efficient training. The findings suggest that DDCL can specifically be of benefit to medical applications where data is often limited and indicate promising directions for future research in domains that involve limited datasets.

Even though reinforcement-learning-based algorithms achieved superhuman performance in many domains, the field of robotics poses significant challenges as the state and action spaces are continuous, and the reward function is predominantly sparse. Furthermore, on many occasions, the agent is devoid of access to any form of demonstration. Inspired by human learning, in this work, we propose a method named highlight experience replay (HiER) that creates a secondary highlight replay buffer for the most relevant experiences. For the weights update, the transitions are sampled from both the standard and the highlight experience replay buffer. It can be applied with or without the techniques of hindsight experience replay (HER) and prioritized experience replay (PER). Our method significantly improves the performance of the state-of-the-art, validated on 8 tasks of three robotic benchmarks. Furthermore, to exploit the full potential of HiER, we propose HiER+ in which HiER is enhanced with an arbitrary data collection curriculum learning method. Our implementation, the qualitative results, and a video presentation are available on the project site: http://www.danielhorvath.eu/hier/.