Transformers for Natural Language Processing and Computer Vision : Specify, verify, and defend production LLM, agentic, RAG, MCP, and multimodal AI systems (4TH)

  • 予約

Transformers for Natural Language Processing and Computer Vision : Specify, verify, and defend production LLM, agentic, RAG, MCP, and multimodal AI systems (4TH)

  • ただいまウェブストアではご注文を受け付けておりません。 ⇒古書を探す
  • 製本 Paperback:紙装版/ペーパーバック版
  • 言語 ENG
  • 商品コード 9781808655555

Full Description

Build transformer systems that reason, retrieve, use tools, and understand images, then prove them in production with semantic blueprints, graded pass/fail evaluation, RAG, MCP agents, fine-tuning, and self-hosted inference.

Key Features

Paste-ready semantic blueprints your copilot turns into working code in your own stack
Formal Verification & Validation (V&V) harnesses that grade builds on pass/fail criteria
Engineer RAG, MCP agents, memory, adaptation, and multimodal AI across frontier and open-weight models

Book DescriptionTransformer code is easy to generate, but production judgment is not. Teams must choose models, assemble context, control tools, measure quality, protect data, and manage cost. Transformers for NLP and Computer Vision, Fourth Edition, provides a framework across frontier APIs and open-weight models.

This edition bridges the Third Edition's transformer and computer vision foundations with the Fourth Edition's focus on reasoning models, RAG, agents, multimodal systems, and self-hosted inference. Rather than competing with copilots at producing short-lived code, it publishes the layer copilots cannot generate: eighteen Semantic Blueprints you can paste into your copilot, each defining interfaces, contracts, prohibitions, and a harness that grades the result against pass/fail criteria. You will cover transformer architecture, KV caches, reasoning models, context engineering, API gateways, production RAG, MCP agents, memory, LoRA/QLoRA, guardrails, red teaming, LLM-as-a-judge evaluation, observability, vision-language models, document understanding, vLLM serving, quantization, and sovereign deployment.

Every chapter follows a blueprint-first method, links implementation choices to cost, security, governance, and auditability, and provides hands-on work for Colab or consumer GPUs, with enterprise notes for scaling acceptance tests.What you will learn

Read the 2024-2026 shift and what it changed about the job
Instrument attention, KV cache, MoE, and reasoning models on free GPUs
Engineer budgeted, verified context beyond prompt engineering
Build provider-proof gateways, RAG retrieval contracts, and MCP agents
Decide between fine-tuning and context with defensible matrices
Assemble an evaluation spine with golden sets and calibrated judges
Route multimodal pipelines and serve them with vLLM-class engines
Compose, evaluate, and certify a complete production AI system

Who this book is forThis book is for solution architects, senior AI/ML engineers, platform engineers, software developers, data scientists, and applied researchers who must move LLM, agentic, and multimodal systems from prototype to production under security, cost, and audit constraints. It also serves readers of the first three editions who need the bridge from making a model run to proving a system ships, the courses built on those editions, and CTOs who buy architectural judgment rather than tutorials.
Intermediate to advanced: working Python is assumed, and every exercise runs on free-tier hardware.

Contents

Table of Contents

What Are Post-Discovery Era Transformers?
The Architecture — Attention, Tokenizers, Embeddings, and the KV Cache
Reasoning Models and Inference-Time Compute
From Prompt to Context Engineering
The API Layer as Contract
RAG — The Retrieval Contract
Orchestration Invariants
Agentic AI and MCP
Memory and State
Fine-Tuning vs. Context — The Adaptation Decision
Interpretability, Safety, and Guarding the Giants
Evaluation and Observability: The Durable Layer
Vision Transformers and Multimodal LLMs
Generative Vision — Diffusion and Beyond
Multimodal Pipelines in Production
Self-Hosted Inference
Production Architectures and Sovereign Deployment
Capstone — Assembling the Production System

最近チェックした商品