The classic greedy coloring algorithm considers the vertices of an input graph G in a given order and assigns the first available color to each vertex v in G. In the Grundy Coloring problem, the task is to find an ord...
详细信息
As the cornerstone of artificial intelligence, machine perception confronts a fundamental threat posed by adversarial illusions. These adversarial attacks manifest in two primary forms: deductive illusion, where speci...
详细信息
This research investigates the application of state-of-the-art machine learning strategies, including deep learning, clustering, and reinforcement learning, to better understand user behavior in the banking sector. Th...
详细信息
ISBN:
(数字)9798331537555
ISBN:
(纸本)9798331537562
This research investigates the application of state-of-the-art machine learning strategies, including deep learning, clustering, and reinforcement learning, to better understand user behavior in the banking sector. This strategy enriches personalisation, boosts customer engagement, and enhances operational efficiencies. Advanced neural network designs, including Recurrent Neural Networks (RNNs) and transformer architectures, are deployed to interpret transactional and communicative data. Various clustering methods, such as K-Means, DBSCAN, and Hierarchical Clustering, are utilised to classify users by their behavioral characteristics. Moreover, techniques like Deep Q-learning and multi-agent reinforcement learning are employed to adapt dynamically to user actions, thereby maximizing satisfaction. The research further highlights essential ethical issues concerning bias minimization, privacy protection, and the interpretability of models, ensuring the ethical deployment of machine learning practices. Through empirical validation, the suggested framework shows notable improvements in predicting defaults, refining marketing approaches, and increasing adoption rates. These findings underscore the revolutionary influence of machine learning in profiling user behavior, hinting at future developments in federated learning and quantum computing.
This paper explores the algebraic conditions under which a cellular automaton with a non-linear local rule exhibits surjectivity and reversibility. We also analyze the role of permutivity as a key factor influencing t...
详细信息
This study highlights the rapid advancements in artificial intelligence (AI) and machine learning (ML), which have transformed the financial sector by enhancing personalised user interactions and customer engagement. ...
详细信息
ISBN:
(数字)9798331537555
ISBN:
(纸本)9798331537562
This study highlights the rapid advancements in artificial intelligence (AI) and machine learning (ML), which have transformed the financial sector by enhancing personalised user interactions and customer engagement. An innovative AI-driven framework was proposed to deliver real-time, context-aware, and highly personalised responses for Digital Banking users. The system architecture employs advanced ML models, natural language processing (NLP) techniques, and modern front-end technologies such as React and GraphQL to address the challenges related to data silos, computational demand, and data privacy. ML models such as user segmentation, recommendation, and NLP models work together to analyse user behaviour, predict needs, and generate human-like responses. Utilising React, GraphQL subscriptions, and Edge AI, the front-end layer ensures a seamless and responsive user experience. The experimental results showed a 120% increase in click-through rates, a 180% increase in follow-up actions, and a 70% reduction in average response time, demonstrating significant improvements in user engagement. User satisfaction, measured by the Net Promoter Score, was significantly higher for the personalised system (8.5) than for the traditional system (5.2). The proposed methodology lays the foundation for an agile trust-based financial environment. Future enhancements will focus on explainable AI, multimodal interactions, and blockchain integration to boost transparency, engagement, and data privacy.
The rapid advancements in digital technologies such as artificial intelligence (AI), virtual reality (VR), augmented reality (AR), mixed reality (MR), extended reality (XR), and the internet of things (IoT) have revol...
详细信息
Federated Learning (FL) offers a privacy-preserving solution by enabling multiple clients to train a shared model collaboratively without centralizing data. However, the decentralized nature of FL presents challenges,...
详细信息
ISBN:
(数字)9798331507817
ISBN:
(纸本)9798331507824
Federated Learning (FL) offers a privacy-preserving solution by enabling multiple clients to train a shared model collaboratively without centralizing data. However, the decentralized nature of FL presents challenges, particularly regarding security and performance under adversarial conditions. This paper investigates the effects of poisoning attacks under data heterogeneity. Our experiments evaluate the impact of varying malicious client fractions and poison concentration levels on the accuracy of the model. We explore the effects of poisoning attacks on FedAvg and FedNova models using medical imaging tasks. Our findings reveal that increasing data heterogeneity exacerbates the effects of poisoning, with FedNova demonstrating greater resilience compared to FedAvg. We found that the number of malicious clients plays a more significant role in degrading performance than the ratio of poisoning samples shared by each malicious client, suggesting that even modest levels of poisoning can be tolerated by most algorithms. The study highlights the importance of developing robust defense mechanisms to maintain model performance under adversarial conditions.
The increasing demand for large annotated datasets in computer vision underscores the need for scalable synthetic data generation methods, as traditional approaches often lack adaptability or offer limited annotations...
暂无评论