Ken Huang is an acclaimed author of 8 books on AI and Web3. He is the Co-Chair of the AI Organizational Responsibility Working Group and AI Control Framework at the Cloud Security Alliance.In addition, Huang contributed extensively to key initiatives in the space. He is a core contributor to OWASP's Top 10 Risks for LLM Applications and heavily involved in the NIST Generative AI Public Working Group. He also provides feedback on publications like NIST SP 800-226.A sought-after speaker, Ken has shared his insights at renowned global conferences, including those hosted by Davos WEF, ACM, IEEE, and CSA AI Summit, CSA AI Think Tank Day and World Bank. His recent co-authorship of "Blockchain and Web3: Building the Cryptocurrency, Privacy, and Security Foundations of the Metaverse" adds to his reputation, with the book being recognized as one of the must-reads in both 2023 and 2024 by TechTarget.

• Table of ContentsIntroduction to LLM Design PatternsData Cleaning for LLM TrainingData AugmentationHandling Large Datasets for LLM TrainingData VersioningDataset Annotation and LabelingTraining PipelineHyperparameter TuningRegularizationCheckpointing and RecoveryFine-TuningModel PruningQuantizationEvaluation MetricsCross-ValidationInterpretabilityFairness and Bias DetectionAdversarial RobustnessReinforcement Learning from Human FeedbackChain-of-Thought PromptingTree-of-Thoughts PromptingReasoning and ActingReasoning WithOut ObservationReflection TechniquesAutomatic Multi-Step Reasoning and Tool UseRetrieval-Augmented Generation Graph-Based RAGAdvanced RAGEvaluating RAG SystemsAgentic Patterns

Ken Huang is an acclaimed author of 8 books on AI and Web3. He is the Co-Chair of the AI Organizational Responsibility Working Group and AI Control Framework at the Cloud Security Alliance.In addition, Huang contributed extensively to key initiatives in the space. He is a core contributor to OWASP's Top 10 Risks for LLM Applications and heavily involved in the NIST Generative AI Public Working Group. He also provides feedback on publications like NIST SP 800-226.A sought-after speaker, Ken has shared his insights at renowned global conferences, including those hosted by Davos WEF, ACM, IEEE, and CSA AI Summit, CSA AI Think Tank Day and World Bank. His recent co-authorship of "Blockchain and Web3: Building the Cryptocurrency, Privacy, and Security Foundations of the Metaverse" adds to his reputation, with the book being recognized as one of the must-reads in both 2023 and 2024 by TechTarget.

• Table of ContentsIntroduction to LLM Design PatternsData Cleaning for LLM TrainingData AugmentationHandling Large Datasets for LLM TrainingData VersioningDataset Annotation and LabelingTraining PipelineHyperparameter TuningRegularizationCheckpointing and RecoveryFine-TuningModel PruningQuantizationEvaluation MetricsCross-ValidationInterpretabilityFairness and Bias DetectionAdversarial RobustnessReinforcement Learning from Human FeedbackChain-of-Thought PromptingTree-of-Thoughts PromptingReasoning and ActingReasoning WithOut ObservationReflection TechniquesAutomatic Multi-Step Reasoning and Tool UseRetrieval-Augmented Generation Graph-Based RAGAdvanced RAGEvaluating RAG SystemsAgentic Patterns

Ken Huang is an acclaimed author of 8 books on AI and Web3. He is the Co-Chair of the AI Organizational Responsibility Working Group and AI Control Framework at the Cloud Security Alliance.In addition, Huang contributed extensively to key initiatives in the space. He is a core contributor to OWASP's Top 10 Risks for LLM Applications and heavily involved in the NIST Generative AI Public Working Group. He also provides feedback on publications like NIST SP 800-226.A sought-after speaker, Ken has shared his insights at renowned global conferences, including those hosted by Davos WEF, ACM, IEEE, and CSA AI Summit, CSA AI Think Tank Day and World Bank. His recent co-authorship of "Blockchain and Web3: Building the Cryptocurrency, Privacy, and Security Foundations of the Metaverse" adds to his reputation, with the book being recognized as one of the must-reads in both 2023 and 2024 by TechTarget.

• Table of ContentsIntroduction to LLM Design PatternsData Cleaning for LLM TrainingData AugmentationHandling Large Datasets for LLM TrainingData VersioningDataset Annotation and LabelingTraining PipelineHyperparameter TuningRegularizationCheckpointing and RecoveryFine-TuningModel PruningQuantizationEvaluation MetricsCross-ValidationInterpretabilityFairness and Bias DetectionAdversarial RobustnessReinforcement Learning from Human FeedbackChain-of-Thought PromptingTree-of-Thoughts PromptingReasoning and ActingReasoning WithOut ObservationReflection TechniquesAutomatic Multi-Step Reasoning and Tool UseRetrieval-Augmented Generation Graph-Based RAGAdvanced RAGEvaluating RAG SystemsAgentic Patterns