Yazar "Zitar, Raed Abu" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Deep Reinforcement Learning: Bridging Learning and Control in Intelligent Systems
    (CRC Press, 2025) Izci, Davut; Thanh, Hung Vo; Zitar, Raed Abu; Al-Okbi, Nada Khalil; Liu, Zhe; Şahin, Canan Batur; Abualigah, Laith
    Deep Reinforcement Learning (DRL) has gained popularity as a new approach in artificial intelligence that successfully integrates representation learning through Deep Learning with decision making in Reinforcement Learning. In this work, we investigate basic concepts of DRL design, structural composition, and scope of usage in intelligent systems. More specifically, several benchmark tasks were assigned to test states and actions of DRL algorithms such as Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO). Empirical evaluations illustrate the potential of DRL in dealing with complex tasks. Sample efficiency, stability and interpretability issues of DRL are also reviewed in the paper. Suggestions for further work are concentrated on algorithm increase of robustness, training time and expense decrease as well as enhancement of implementation efficiency in practical environment. © 2025 Laith Abualigah.
  • Küçük Resim Yok
    Öğe
    The Evolution of Machine Learning: From Traditional Algorithms to Deep Learning Paradigms
    (CRC Press, 2025) Alomari, Saleh Ali; Abdel-Salam, Mahmoud; Raza, Ali; Şahin, Canan Batur; Zitar, Raed Abu; Zhang, Peiying; Snasel, Vaclav
    There has been a noticeable development in the area of machine learning (ML) over the last few decades, transitioning from conventional algorithm-based systems to neural networks. The goal of this chapter is to portray the evolution of machine learning, highlighting important steps, primary algorithms, and the development of mono-approach neural network modeling. We examine the various methodologies developed in the field, including supervised, unsupervised, and reinforcement learning, and explain how deep learning architectures have transformed image recognition and natural language processing, and autonomous systems. The chapter concludes by addressing existing issues in machine learning, most notably interpretability, bias and the computational complexity, while suggesting directions for future research in this active field. © 2025 Laith Abualigah.