Hasil untuk "machine learning"

Alejandro Barredo Arrieta, Natalia Díaz Rodríguez, J. Ser et al.

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

Zonghan Wu, Shirui Pan, Fengwen Chen et al.

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial–temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.

Leland McInnes, John Healy

UMAP (Uniform Manifold Approximation and Projection) is a novel manifold learning technique for dimension reduction. UMAP is constructed from a theoretical framework based in Riemannian geometry and algebraic topology. The result is a practical scalable algorithm that applies to real world data. The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance. Furthermore, UMAP has no computational restrictions on embedding dimension, making it viable as a general purpose dimension reduction technique for machine learning.

Adam Paszke, Sam Gross, Soumith Chintala et al.

Adina Williams, Nikita Nangia, Samuel R. Bowman

This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding. At 433k examples, this resource is one of the largest corpora available for natural language inference (a.k.a. recognizing textual entailment), improving upon available resources in both its coverage and difficulty. MultiNLI accomplishes this by offering data from ten distinct genres of written and spoken English, making it possible to evaluate systems on nearly the full complexity of the language, while supplying an explicit setting for evaluating cross-genre domain adaptation. In addition, an evaluation using existing machine learning models designed for the Stanford NLI corpus shows that it represents a substantially more difficult task than does that corpus, despite the two showing similar levels of inter-annotator agreement.

Tianqi Chen, Carlos Guestrin

Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges. We propose a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning. More importantly, we provide insights on cache access patterns, data compression and sharding to build a scalable tree boosting system. By combining these insights, XGBoost scales beyond billions of examples using far fewer resources than existing systems.

Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally varound the prediction. We also propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). We show the utility of explanations via novel experiments, both simulated and with human subjects, on various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and identifying why a classifier should not be trusted.

J. Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz et al.

Significance Deep neural networks are currently the most successful machine-learning technique for solving a variety of tasks, including language translation, image classification, and image generation. One weakness of such models is that, unlike humans, they are unable to learn multiple tasks sequentially. In this work we propose a practical solution to train such models sequentially by protecting the weights important for previous tasks. This approach, inspired by synaptic consolidation in neuroscience, enables state of the art results on multiple reinforcement learning problems experienced sequentially. The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Until now neural networks have not been capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is possible to overcome this limitation and train networks that can maintain expertise on tasks that they have not experienced for a long time. Our approach remembers old tasks by selectively slowing down learning on the weights important for those tasks. We demonstrate our approach is scalable and effective by solving a set of classification tasks based on a hand-written digit dataset and by learning several Atari 2600 games sequentially.

N. Japkowicz, Mohak Shah

Yoshua Bengio, Yann LeCun

R. Vilalta, Youssef Drissi

O. Chapelle, Bernhard Schlkopf, A. Zien

P. Dayan, Geoffrey E. Hinton, Radford M. Neal et al.

Daniel Billsus, M. Pazzani

A. Coates, Brody Huval, Tao Wang et al.

Qingkai Liu, Haitao Jing, Xueying Wen et al.

Accurate, near real-time soybean phenology information is critical for crop management and breeding. Previous approaches relying on satellite remote sensing time-series data suffer from temporal delays, limiting their usefulness for in-season decision-making. To overcome this limitation, this study reframes phenology identification as a near real-time classification task using single-timepoint Unmanned Aerial Vehicle (UAV) imagery collected from 420 soybean germplasm resources across three experimental sites, and proposes an innovative multi-modal dynamic Gating Fusion Model that integrates two optimized pathways. one based on machine learning (ML) and the other on deep learning (DP). In the ML branch, systematic benchmarking of tabular-feature models identified the Soft Voting ensemble as the best classifier. In the DL branch, an enhanced BC-ConvNeXt model equipped with BiFPN and CBAM modules was developed to strengthen visual feature extraction. Building on these two optimal classifiers, the dynamic gating fusion model achieved the highest F1-score of 94.3% across seven key growth stages (V1, V2, R1, R2, R6, R7, R8). This result represents a significant improvement of 1.5% and 10.6% over the best performing ML and DL models, respectively. The superior performance arises from the intelligent arbitration of complementary strengths, with gating-weight analysis revealing a strategy that prioritizes ML predictions while leveraging DL for error correction. This work establishes a complete framework for near real-time crop phenology detection and demonstrates the strong potential of intelligent multi-modal fusion in high-throughput phenotyping.

J. Raymond, S. Lisberger, M. Mauk

Ryusei Sato, Takashi Watanabe

A one-size-fits-all approach to fall risk assessment in older adults has critical limitations. This study aimed to overcome this by identifying distinct gait phenotypes and their specific fall mechanisms using foot-mounted IMU waveform data from 146 older adults (mean age 82.6 ± 6.2 years). A data-driven clustering algorithm identified four phenotypes (Robust, High-cadence, Intermediate, and Cautious), each with different fall prevalence rates (27–68%). Interpretable machine learning (SHAP) revealed that fall trajectories were phenotype-dependent. While physiological declines such as gait speed were the primary cause of falls in the Cautious group, fear of falling (FES-I) was the primary cause in the physically healthy Robust group, suggesting a psychological pathway. Consequently, the optimal Timed Up and Go (TUG) test screening cutoff varied across phenotypes, ranging from 11.95 s to 14.00 s, demonstrating the limitations of a one-size-fits-all approach. These findings demonstrate that fall mechanisms are phenotype-dependent, underscoring the necessity of a personalized assessment strategy to improve fall prevention.

Mohammed N. Alenezi

As digital infrastructure continues to expand, networks, web services, and Internet of Things (IoT) devices become increasingly vulnerable to distributed denial of service (DDoS) attacks. Remarkably, IoT devices have become attracted to DDoS attacks due to their common deployment and limited applied security measures. Therefore, attackers take advantage of the growing number of unsecured IoT devices to reflect massive traffic that overwhelms networks and disrupts necessary services, making protection of IoT devices against DDoS attacks a major concern for organizations and administrators. In this paper, the effectiveness of supervised machine learning (ML) classification and deep learning (DL) algorithms in detecting DDoS attacks on IoT networks was investigated by conducting an extensive analysis of network traffic dataset (legitimate and malicious). The performance of the models and data quality improved when emphasizing the impact of feature selection and data pre-processing approaches. Five machine learning models were evaluated by utilizing the Edge-IIoTset dataset: Random Forest (RF), Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and K-Nearest Neighbors (KNN) with multiple K values, and Convolutional Neural Network (CNN). Findings revealed that the RF model outperformed other models by delivering optimal detection speed and remarkable performance across all evaluation metrics, while KNN (K = 7) emerged as the most efficient model in terms of training time.

Seif Hashem Al-Azzam, Mohammad Al-Oudat

Background/purpose. University students in Jordan face numerous challenges that affect their lifestyle on campus and academic performance. The most common challenges can be summarized into two important categories: psychological and academic factors. Psychological factors, such as anxiety levels and daily sleep duration, and academic factors such as GPA and study hours, it is worth mentioning that these phenomena may have related influences on each other and along with such interactions may heighten negative effects. Furthermore, there is no solid research on the topic that can provide solutions to both dimensions in one study. This paper provides a novel analysis-based framework to help target students who face these challenges in the early stages to provide quality service and consultation. Materials/methods. The framework was developed based on a questionnaire that was built based on consultation of psychological and academic expertise to extract features that are related to the important factors. The questionnaire was distributed to 1020 students from several Jordanian universities. The evaluation of data collected through questionnaires included three major sections about demographic, academic, and psychological factors using the SPSS statistical analysis tool to ensure validity and reliability. After that, the Framework categorizes each student's challenges using the Large Language Model (LLM) into academic difficulties, academic and psychological challenges, psychological distress, and normal students. Finally, multiple classifiers are applied to obtain the status of the students. Results. The results show that the collected features from questionnaires work well with all classifiers with high accuracy. The contributions of this study include analyzing both academic and psychological factors and exploring their correlation through a case study conducted in Jordan. Also, using LLM for categorization along with classifiers provides an early intervention for students who suffer from academic, and psychological challenges or both. Conclusion. These findings suggest that early interventions targeting both academic and psychological factors are critical for improving student well-being and academic success, providing valuable insights for university support services.