Skip to main content
Elsevier

Morgan Kaufmann

  • Advanced Methods for Optimizing and Accelerating Deep Learning Models

    • 1st Edition
    • Patrick Siarry + 3 more
    • English
    Advanced Optimization and Acceleration Techniques for Deep Learning Models provides a comprehensive guide to enhancing deep learning models' efficiency, scalability, and performance, including large language models (LLMs). As AI systems grow in complexity, optimizing their training and deployment has become critical for achieving higher accuracy, faster inference, and reduced computational costs. This book explores cutting-edge optimization strategies, from gradient descent refinements and hyperparameter tuning to model compression, pruning, and hardware acceleration. AI is evolving rapidly, but existing deep learning resources often focus on building models rather than optimizing them for efficiency and scalability. As deep learning applications expand into cloud computing, edge AI, and real-time decision-making, a dedicated resource on optimization is essential. This book addresses this gap by providing a structured approach to making deep learning networks faster, more cost-effective, and more sustainable.

  • Artificial Intelligence Modeling for Dynamical Problems

    • 1st Edition
    • Snehashish Chakraverty + 2 more
    • English
    Artificial Intelligence Modeling for Dynamical Problems provides a comprehensive exploration of AI-driven methodologies tailored to address the intricate challenges posed by dynamical systems. The chapters in this book delve into cutting-edge techniques, including scientific machine learning, operator learning, fuzzy logic, and optimization algorithms, highlighting their applications in structural dynamics, fluid dynamics, robotics, and wave dynamics. Readers will gain insights into innovative state-of-the-art approaches such as Physics-Informed Neural Networks (PINNs) for precise navigation and control in autonomous vehicles, convolutional neural networks (CNNs) for frequency dynamics recognition, and data-driven models for market sentiment analysis. Additionally, the book explores the role of uncertainty modeling, statistical inference, and hybrid AI techniques, such as Type-2 fuzzy fractional modeling, in advancing the field of dynamical system analysis. Each chapter combines foundational principles with practical applications, including recent investigations, making it a valuable resource for researchers, practitioners, students of STEM seeking to apply theoretical AI models to real-world dynamical problems.

  • Functional Equations and Stability Theory

    Methods and Applications in Science and Engineering
    • 1st Edition
    • Ali Turab + 2 more
    • English
    Functional Equations and Stability Theory: Methods and Applications in Science and Engineering presents current advancements in the theory of functional equations and their stability, with a particular emphasis on their applications across science, engineering, and computational domains. Functional equations—long-stand... pillars of mathematical analysis—have experienced a transformative evolution through the lens of Hyers–Ulam stability theory and its generalizations, which now intersect with key disciplines including artificial intelligence, cognitive science, and cybersecurity. This book provides readers with both principles of classical theory along with contemporary applications, thereby advancing the discourse on functional equations beyond its traditional confines. The book provides readers with both foundational studies and emerging methodologies, exploring how stability properties—such as Ulam–Hyers and generalized stability—are not only central to pure mathematics but also critically relevant to the modeling of real-world systems. By presenting methods that span theoretical results, fixed point methods, approximation techniques, and interdisciplinary case studies, this book offers a comprehensive perspective for readers interested in both mathematical rigor and real-world impact.The book features chapters on advanced topics including classical and generalized stability of Cauchy, Jensen, Drygas, and Pexider-type equations; functional equations in restricted domains and abstract metric spaces; fixed point techniques for analyzing nonlinear and operatorial equations; stability in functional inequalities and mixed-type systems; applications to cognitive modeling, behavioral dynamics, and learning systems; functional frameworks in information theory, entropy, and communication systems; operator-valued and matrix functional equations; stability-informed modeling in cybersecurity, robotics, and intelligent environments; and, approximation and numerical approaches to stability problems. As such, the authors address both computational and mathematical dimensions, empowering readers to apply functional equations and stability theory to contemporary scientific problems.

  • Advances in Multimodal Large Language Models for Healthcare

    Methods and Applications
    • 1st Edition
    • Hari Mohan Pandey + 4 more
    • English
    Advances in Multimodal Large Language Models for Healthcare: Methods and Applications provides valuable insights on Large Language Models in healthcare applications for researchers, academics, and practitioners. The book explains key concepts, including artificial intelligence, machine learning, deep learning, and the evolution of neural networks and transformer models. It then covers generative AI and LLMs for a wide spectrum of healthcare applications, including mental health, clinical decision support, interactive system design, and sensitive analysis. Readers will find this to be a valuable deep dive into the emergent intersection of LLMs and health care, with guidance into applications, technical and programming methods, and more.Although LLMs have shown some promising results in the healthcare sector, numerous challenges need to be addressed before they can be used in patient care. The two key issues with the adoption of LLMs regarding healthcare settings are reliability, transparency, interpretation of results and bias (data and algorithm) management. Unless properly and adequately validated, there may be incorrect medical information provided by the LLM-based systems, which can lead to misdiagnosis or hazardous treatment errors. At this point, LLMs have not only been used for decision making or documentation, they have also proven to be useful in patient engagement through QA systems, medical chatbots, and virtual healthcare.

  • Trustworthy LLMs

    Principles and Challenges
    • 1st Edition
    • Mohit Kumar
    • English
    Despite numerous advantages, LLMs have trust, transparency, accountability, and reliability issues due to development with "black-box" approaches, which make it difficult to understand how LLMs create specific outputs. Trustworthy LLMs: Principles and Challenges presents the fundamental concepts of trustworthy LLMs, then proceeds to address the foremost challenges researchers and developers face in developing reliable and trustworthy LLMs. The book begins by presenting the main research branches of artificial intelligence along with the principles of LLMs, from pre-training to fine tuning, and, ultimately, trustworthy LLMs. Readers will learn about the chief technical principles of LLMs, including attention mechanism, transformers, and transfer learning. The methodologies used for development of ChatGPT have been explained as a case study for comprehensive understanding of the concepts involved in LLMs. Readers will also learn about the integration of XAI with LLM, and other key frontiers in trustworthy LLM development, including the synergy between deep learning and LLMs, as well as case studies on GPT-4 and OPT-1.3B. The book concludes with chapters on key challenges and future research approaches for developing trustworthy LLMs.

  • Measuring the User Experience

    Collecting, Analyzing, and Presenting UX Metrics
    • 4th Edition
    • Bill Albert + 1 more
    • English
    Measuring the User Experience: Collecting, Analyzing, and Presenting UX Metrics provides the quantitative analysis training that students and professionals need. This book presents an update on the first resource that focused on how to quantify user experience. Now in its fourth edition, the authors have continued to expand on the area of behavioral and physiological metrics. The book also contains new research and updated examples, several new case studies, and new examples using the most recent version of Excel.

  • Observing the User Experience

    A Practitioner's Guide to User Research
    • 3rd Edition
    • Elizabeth Goodman + 1 more
    • English
    Observing the User Experience: A Practitioner's Guide to User Research, Third Edition helps readers bridge the gap to understand what users want and need from their product. Filled with real-world experience and a wealth of practical information, the book presents a complete toolbox of techniques to help designers, developers, and other stakeholders see through the eyes of their users. Sections discuss the benefits of end-user research and the ways it fits into the development of useful, desirable, and successful products and present techniques for understanding people’s needs, desires, and abilities, providing a basis for developing better products, whether Web, software, or mobile-based.Final chapters explain the communication and application of research results.

  • Probabilistic Modelling for Advanced Data Analysis

    • 1st Edition
    • Amit Kumar Tyagi
    • English
    Probabilistic Modelling for Advanced Data Analysis provides a practical and rigorous guide for data practitioners to effectively implement probabilistic models in real-world scenarios. The book strikes a balance between high-level intuition and technical derivations, offering step-by-step explanations, real-world case studies, and Python implementation examples. The authors offer specific solutions that include modeling and quantifying uncertainty in data-driven decision-making, applying Bayesian inference to real-world problems and implementing scalable probabilistic models for large-scale datasets, all of which contribute to explainable and trustworthy AI.This book presents readers with theoretical foundations and practical applications of probabilistic modeling, providing a structured approach for researchers, data scientists, and industry professionals. It meets the increasing demand for uncertainty-aware AI models, Bayesian inference, and probabilistic graphical models across various fields of research.

  • Neural Networks

    A Concise Theoretical Foundation
    • 1st Edition
    • Aydin Sarraf + 1 more
    • English
    This book presents deep learning as both a mathematical discipline and an applied field, connecting theoretical principles with the modeling and design choices that shape modern neural systems. It explores how neural networks are formulated and how they learn, from multilayer perceptrons, activation and loss functions, optimization, and backpropagation to questions of expressivity and generalization. These ideas are applied to neural architectures for different forms of data, including convolutional, recurrent, and graph neural networks, with attention to the mathematical principles, training challenges, and design choices that distinguish them. The book then turns to generative models and sequential decision-making, covering variational and adversarial models, diffusion, and reinforcement learning.The later parts follow the evolution of neural networks toward increasingly general systems, exploring attention and transformer architectures, multimodal models, large language models, retrieval-augmented systems, and autonomous agents. The book also considers directions beyond conventional deep learning, including continuous-time and physics-informed neural networks, biologically-inspire... and neuromorphic models, Bayesian approaches to uncertainty, and quantum neural networks.The term “theoretical” in the title, Neural Networks: A Concise Theoretical Foundation, refers to the mathematical formulation of neural networks, not to a comprehensive, proof-oriented treatment of neural network theory. Organized in four parts, the book connects mathematical descriptions with the architectures, learning methods, and emerging directions that continue to shape neural computation.

  • Advanced Concepts in Grey Wolf Optimizer

    Leading the Pack in Advanced Optimization
    • 1st Edition
    • Seyedali Mirjalili
    • English
    Advanced Concepts in Grey Wolf Optimizer: Leading the Pack in Advanced Optimization provides in-depth coverage of recent theoretical advancements in GWO, as well as advanced methods to handle issues such as multiple objectives, constraints, binary variables, large search spaces, dynamic goals, and uncertain data. This book assumes familiarity with optimization fundamentals and therefore dives directly into multi-objective, constrained, binary, and dynamic-environment variants, as well as GWO-ML/LLM hybrids. Extensive real-world case studies in areas such as energy systems, supply-chain design, LLM fine-tuning, robotics, and finance ensure that both scholars and engineers can translate the material into deployable solutions. The authors present important new theories, hybrids with Machine Learning/Deep Learning, and hybrid methods that increase GWO’s performance. The use of generative AI to improve this algorithm and make it more generic is also explored, along with diverse applications across multiple fields to illustrate the practical utility and versatility of the methods presented. Written by some of the world’s most highly cited researchers in the field of artificial intelligence, algorithms, and machine learning, the book serves as an advanced resource for researchers and practitioners interested in applying and developing the Grey Wolf Optimizer.

Browse by Publisher