本套课程设计AI人工智能内容讲解，源视频为英文，含英文字幕文件，可翻译成中文。
视频课程全面覆盖了人工智能（AI）的核心领域，从基础知识到高级应用，适合不同层次的学习者。课程从AI入门模块开始，逐步介绍数据的重要性、关键技术、生成式AI及其实际挑战，帮助学习者建立扎实的理论基础。接着，Python模块详细讲解了编程环境搭建、语法基础、函数与迭代等核心概念，为后续的AI开发打下坚实的编程基础。
自然语言处理（NLP）模块深入探讨了文本预处理、情感分析、文本分类等关键技术，并通过案例研究（如假新闻分类）帮助学习者将理论应用于实践。大语言模型（LLMs）模块则聚焦于Transformer架构、GPT模型、BERT问答模型等前沿技术，结合Hugging Face等工具，帮助学习者掌握最新的AI模型应用。
此外，课程还涵盖了LangChain、向量数据库、语音识别等新兴领域，特别是LangChain模块详细介绍了如何构建智能对话系统、检索增强生成（RAG）等技术，极具实用性。语音识别模块则从声音基础到OpenAI的Whisper模型，全面解析了语音转文字的技术细节。
无论你是AI初学者，还是希望深入掌握大语言模型和语音识别技术的开发者，这门课程都能为你提供系统化的学习路径和实战经验，助你在AI领域快速成长。
├── 01. Intro to AI Module Getting started
├── 02. Intro to AI Module Data is essential for building AI
├── 03. Intro to AI Module Key AI techniques
├── 04. Intro to AI Module Important AI branches
├── 05. Intro to AI Module Understanding Generative AI
├── 06. Intro to AI Module Practical challenges in Generative AI
├── 07. Intro to AI Module The AI tech stack
├── 08. Intro to AI Module AI job positions
├── 09. Intro to AI Module Looking ahead
├── 10. Python Module Why Python
├── 11. Python Module Setting Up the Environment
├── 12. Python Module Python Variables and Data Types
├── 13. Python Module Basic Python Syntax
├── 14. Python Module More on Operators
├── 15. Python Module Conditional Statements
├── 16. Python Module Functions
├── 17. Python Module Sequences
├── 18. Python Module Iteration
├── 19. Python Module A Few Important Python Concepts and Terms
├── 20. NLP Module Introduction
├── 21. NLP Module Text Preprocessing
├── 22. NLP Module Identifying Parts of Speech and Named Entities
├── 23. NLP Module Sentiment Analysis
├── 24. NLP Module Vectorizing Text
├── 25. NLP Module Topic Modelling
├── 26. NLP Module Building Your Own Text Classifier
├── 27. NLP Module Categorizing Fake News (Case Study)
├── 28. NLP Module The Future of NLP
├── 29. LLMs Module Introduction to Large Language Models
├── 30. LLMs Module The Transformer Architecture
├── 31. LLMs Module Getting Started With GPT Models
├── 32. LLMs Module Hugging Face Transformers
├── 33. LLMs Module Question and Answer Models With BERT
├── 34. LLMs Module Text Classification With XLNet
├── 35. LangChain Module Introduction
├── 36. LangChain Module Tokens, Models, and Prices
├── 37. LangChain Module Setting Up the Environment
├── 38. LangChain Module The OpenAI API
├── 39. LangChain Module Model Inputs
├── 40. LangChain Module Message History and Chatbot Memory
├── 41. LangChain Module Output Parsers
├── 42. LangChain Module LangChain Expression Language (LCEL)
├── 43. LangChain Module Retrieval Augmented Generation (RAG)
├── 44. LangChain Module Tools and Agents
├── 45. Vector Databases Module Introduction
├── 46. Vector Databases Module Basics of Vector Space and High-Dimensional Data
├── 47. Vector Databases Module Introduction to The Pinecone Vector Database
├── 48. Vector Databases Module Semantic Search with Pinecone and Custom (Case Study)
├── 49. Speech Recognition Module Introduction
├── 50. Speech Recognition Module Sound and Speech Basics
├── 51. Speech Recognition Module Analog to Digital Conversion
├── 52. Speech Recognition Module Audio Feature Extraction for AI Applications
├── 53. Speech Recognition Module Technology Mechanics
├── 54. Speech Recognition Module Setting Up the Environment
├── 55. Speech Recognition Module Transcribing Audio with Google Web Speech API
├── 56. Speech Recognition Module Background Noise and Spectrograms
├── 57. Speech Recognition Module Transcribing Audio with OpenAI's Whisper
├── 58. Speech Recognition Module Final Discussion and Future Directions
├── 59. LLM Engineering Module Introduction
├── 60. LLM Engineering Module Planning stage
├── 61. LLM Engineering Module Crafting and Testing AI Prompts
├── 62. LLM Engineering Module Getting to Know Streamlit
├── 63. LLM Engineering Module Developing the prototype