Search results for "Generative AI Math"
Items we need to order for you
Building Generative AI Agents
The dawn of AI agents is upon us. Tech visionaries like Bill Gates, Andrew Ng, and Vinod Khosla have highlighted the monumental potential of this powerful technology. This book will provide the knowledge and tools necessary to build generative AI agents using the most popular frameworks, such as AutoGen, LangChain, LangGraph, CrewAI, and Haystack. Recent breakthroughs in large language models have opened up unprecedented possibilities. After years of gradual progress in machine learning and deep learning, we are now witnessing novel approaches capable of understanding, reasoning, and generating content in ways that promise to revolutionize nearly every industry. This platform shift is as significant as the advent of mainframes, PCs, cloud computing, mobile technology, and social media. It's why the world's largest technology companies - like Microsoft, Apple, Google, and Meta - are making enormous investments in this category. While chatbots like ChatGPT, Claude, and Gemini have demonstrated remarkable potential, the years ahead will see the rise of generative AI agents capable of executing complex tasks on behalf of users. These agents already exhibit capabilities such as running test suites, searching the web for documentation, writing software, answering questions based on vast organized information, and performing intricate web-based tasks across multiple domains. They can autonomously investigate cybersecurity incidents and address complex customer support needs. By integrating skills, knowledge bases, planning frameworks, memory, and feedback loops, these systems can handle many tasks and improve over time. Building Generative AI Agents serves as a high-quality guide for developers to understand when and where AI agents can be useful, their advantages and disadvantages, and practical advice on designing, building, deploying, and monitoring them. What You Will Learn The foundational concepts, capabilities, and potential of AI agents.Recent innovations in large language models that have enabled the development of AI agents.How to build AI agents for launching a product, creating a financial plan, handling customer service, and using Retrieval Augmented Generation (RAG).Essential frameworks for building generative AI agents, including AutoGen, LangChain, LangGraph, CrewAI, and Haystack.Step-by-step guidance on designing, building, and deploying AI agents.Insights into the future of AI agents and their potential impact on various industries. Who This Book Is For Experienced software developers
R 1,254.00
Generative AI for Business Innovation
This book is a comprehensive guide for business leaders, CXOs, and technical architects looking to adopt Generative AI technologies to create innovative applications for their organizations and clients. The book is divided into three parts. In Part 1, readers will learn the fundamental concepts of Generative AI, such as foundational models and large language models like ChatGPT. It provides an overview of various Generative AI techniques, including Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). This section helps leaders understand the benefits and risks associated with Generative AI, supported by industry case studies showcasing real-world applications. Part 2 focuses on developing a winning strategy for implementing Generative AI. It discusses choosing the right approach, building the necessary architecture and infrastructure, and ensuring data quality for training models. It also addresses technical challenges like computing power and offers best practices for execution. In Part 3, the book explores best practices for adopting Generative AI, emphasizing governance, talent development, and continuous improvement. It also discusses emerging trends and the societal impact of Generative AI, particularly concerning sustainability. By the end, readers will be equipped with the knowledge and strategies to effectively harness Generative AI, paving the way for innovation in their organizations. What you will learn: What are the various Generative AI technologies - Foundational models, LLM, Auto encoders, GANs, VAEs, RAG, prompt engineering and more.How to build a successful strategy for architecting and implementing Generative AIUnderstand Preprocessing and setting up quality data for training generative AI modelsWhat are the future trends in generative AI to build sustainable and trustworthy solutions Who this book is for: Individuals in leadership positions, such as CEOs, CTOs, CIOs, and other senior executives, who are responsible for driving innovation and strategy. decision-making in their organizations and interested in adopting Gen AI for that purpose. Professionals who design and implement technical solutions and infrastructure using Generative AI and machine learning systems.
R 1,368.00
Foundations of Machine Learning and AI
This book builds a single, coherent pathway from linear algebra to probability and statistical learning—the twin pillars behind modern Data Science, AI, and ML. With equal emphasis on geometry (matrices, spectra, projections) and uncertainty (randomness, estimation, generalization), it equips readers to derive algorithms from first principles and implement them robustly at scale. Throughout, geometric pictures (projections, angles, spectra) and probabilistic arguments (risk, concentration, generalization) are developed side-by-side. Each concept is motivated by a real ML use case—denoising with PCA, ill-conditioning in regression, choosing regularization via validation curves, or accelerating large least-squares with sketching.
R 4,700.26
System-2 Reasoning: from Semantic Anchoring to Causal Intelligence, Volume 2
Large language models can write poetry, pass bar exams, and generate fluent code. Yet they continue to fail in the domains where intelligence must be accountable: distinguishing causation from correlation, recognizing when evidence is insufficient, preserving commitments over time,and correcting their own reasoning failures. This book argues that the transition from pattern matching to genuine reasoning requires a System-2 layer grounded in coordinated diagnosis, audit, causal validation, memory, and meta-cognitive control. The volume develops this architecture from first principles through operational protocols. Semantic Anchoring (UCCT) demonstrates how contextual constraints can bind latent model representations into governed reasoning processes rather than prior-driven completion. Regulated Causal Anchoring (RCA) and RAudit diagnose sycophancy, pathological skepticism, and trace-output inconsistency without relying exclusively on ground-truth supervision. The Causal Abstraction Bridge and the CausalTSK benchmark reveal where models collapse from interventional and counterfactual reasoning back into associative prediction. Epistemic Regret Minimization (ERM) identifies causal shortcuts and failures of warranted inference, while Reinforcement Learning from Epistemic Regret (RLER) transforms those reasoning failures into a structured learning signal. Trivium introduces temporal accountability through a Causal Transaction Log, and Quadrivium integrates contextual, causal, temporal, and meta-cognitive regulation into a unified System-2 MACI architecture. The author's central thesis is that Artificial General Intelligence (AGI) will not emerge from scaling monolithic pattern-completion systems alone. AGI will require architectures capable of explaining why an answer is warranted, refusing conclusions when evidence remains indeterminate, and improving through epistemic failure. Written for researchers, advanced students, and practitioners, this book presents a framework for AI systems that are not merely impressive, but auditable, corrigible, and trustworthy. It is suitable for graduate-level courses in artificial intelligence, multi-agent systems, causal reasoning, and trustworthy AI.
R 3,581.00
Multi-LLM Agent Collaborative Intelligence
Today's large language models excel at pattern recall yet falter on long-range planning, self-critique, context loss, and the tendency of maximum-likelihood training to reward popularity over quality. MACI offers a promising route to AGI by orchestrating specialized LLM agents through explicit protocols rather than enlarging a single model. Several modules remedy complementary weaknesses: adversarial-collaborative debate surfaces hidden assumptions; critical-reading rubrics filter incoherent arguments; information-theoretic signals steer dialogue quantitatively; transactional memory enables reliable long-horizon execution; and a dual-agent ethical court adjudicates outputs. Crucially, MACI also modulates linguistic behavior, tuning each agent's contentiousness and emotional tone, so the collective explores ideas from contrasting, affect-aware perspectives before converging.Fourteen aphorisms distill the framework's philosophy, including "Intelligence emerges from regulated collaboration, not isolated brilliance" and "Exploration must remain in tension with exploitation." Across healthcare diagnosis, investment support, scheduling, supply-chain management, and news-bias mitigation, MACI ensembles deliver significant improvements in reasoning depth, planning horizon, and reliability compared with similar-sized single models. By uniting structured debate, information-theoretic coordination, persistent memory, affect-aware discourse, and deliberative ethics, MACI demonstrates that rigorously validated multi-agent collaboration provides a practical, interpretable path toward robust general intelligence.
R 2,746.00
Optimizing Generative AI Workloads for Sustainability
This comprehensive guide provides practical strategies for optimizing Generative AI systems to be more sustainable and responsible. As advances in Generative AI such as large language models accelerate, optimizing these resource-intensive workloads for efficiency and alignment with human values grows increasingly urgent.The book starts with the concept of Generative AI and its wide-ranging applications, while also delving into the environmental impact of AI workloads and the growing importance of adopting sustainable AI practices. It then delves into the fundamentals of efficient AI workload management, providing insights into understanding AI workload characteristics, measuring performance, and identifying bottlenecks and inefficiencies. Hardware optimization strategies are explored in detail, covering the selection of energy-efficient hardware, leveraging specialized AI accelerators, and optimizing hardware utilization and scheduling for sustainable operations. You are also guided through software optimization techniques tailored for Generative AI, including efficient model architecture, compression, and quantization methods, and optimization of software libraries and frameworks. Data management and preprocessing strategies are also addressed, emphasizing efficient data storage, cleaning, preprocessing, and augmentation techniques to enhance sustainability throughout the data life cycle. The book further explores model training and inference optimization, cloud and edge computing strategies for Generative AI, energy-efficient deployment and scaling techniques, and sustainable AI life cycle management practices, and concludes with real-world case studies and best practicesBy the end of this book, you will take away a toolkit of impactful steps you can implement to minimize the environmental harms and ethical risks of Generative AI. For organizations deploying any type of generative model at scale, this essential guide provides a blueprint for developing responsible AI systems that benefit society. What You Will LearnUnderstand how Generative AI can be more energy-efficient through improvements such as model compression, efficient architecture, hardware optimization, and carbon footprint trackingKnow the techniques to minimize data usage, including evaluation, filtering, synthesis, few-shot learning, and monitoring data demands over timeUnderstand spanning efficiency, data minimization, and alignment for comprehensive responsibilityKnow the methods for detecting, understanding, and mitigating algorithmic biases, ensuring diversity in data collection, and monitoring model fairness Who This book Is ForProfessionals seeking to adopt responsible and sustainable practices in their Generative AI work; leaders and practitioners who need actionable strategies and recommendations that can be implemented directly in real-world systems and organizational workflows; ML engineers and data scientists building and deploying Generative AI systems in industry set
R 1,254.00
Mastering Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) represents the cutting edge of AI innovation, bridging the gap between large language models (LLMs) and real-world knowledge. This book provides the definitive roadmap for building, optimizing, and deploying enterprise-grade RAG systems that deliver measurable business value. This comprehensive guide takes you beyond basic concepts to advanced implementation strategies, covering everything from architectural patterns to production deployment. You'll explore proven techniques for document processing, vector optimization, retrieval enhancement, and system scaling, supported by real-world case studies from leading organizations. Key Learning Objectives Design and implement production-ready RAG architectures for diverse enterprise use cases Master advanced retrieval strategies including graph-based approaches and agentic systems Optimize performance through sophisticated chunking, embedding, and vector database techniques Navigate the integration of RAG with modern LLMs and generative AI frameworks Implement robust evaluation frameworks and quality assurance processes Deploy scalable solutions with proper security, privacy, and governance controls Real-World Applications Intelligent document analysis and knowledge extraction Code generation and technical documentation systems Customer support automation and decision support tools Regulatory compliance and risk management solutions Whether you're an AI engineer scaling existing systems or a technical leader planning next-generation capabilities, this book provides the expertise needed to succeed in the rapidly evolving landscape of enterprise AI. What You Will Learn Architecture Mastery: Design scalable RAG systems from prototype to enterprise production Advanced Retrieval: Implement sophisticated strategies, including graph-based and multi-modal approaches Performance Optimization: Fine-tune embedding models, vector databases, and retrieval algorithms for maximum efficiency LLM Integration: Seamlessly combine RAG with state-of-the-art language models and generative AI frameworks Production Excellence: Deploy robust systems with monitoring, evaluation, and continuous improvement processes Industry Applications: Apply RAG solutions across diverse enterprise sectors and use cases Who This Book Is For Primary audience: Senior AI/ML engineers, data scientists, and technical architects building production AI systems; secondary audience: Engineering managers, technical leads, and AI researchers working with large-scale language models and information retrieval systems Prerequisites: Intermediate Python programming, basic understanding of machine learning concepts, and familiarity with natural language processing fundamentals
R 2,264.25
