|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/python-genai-from-scratch/
课程评论：没有评论
课程名称：Jumpstart Python & Gen AI: 从零到英雄的初学者课程 课程概述： 本课程共16节讲座，旨在为初学者提供扎实的Python编程基础和生成性人工智能（Generative AI）的介绍。课程结合理论课程和实践项目，确保学习者能够在实际场景中应用所学知识。通过叙事格式进行讲解，为初学者提供沉浸式的学习体验。 课程结构： - **讲座1**：生成性AI和Python的介绍 - 课程结构和目标概述 - Python的重要性及其在人工智能中的应用 - 生成性AI的概述，以及它在当今世界的相关性 - **Python基础（讲座2-10）** - **讲座2**：Python基础 - 编程和Python语言的概述 - 使用Google Colab进行编码 - 探索GitHub进行代码存储和协作 - Python的基本语法：打印语句、注释 - **讲座3**：变量和数据类型 - 理解变量在编程中的角色 - 探索不同的数据类型：整数、浮点数、字符串 - 使用input()和print()进行简单的输入和输出操作 - **讲座4**：控制结构 - 条件语句：if, elif, else - 比较和逻辑运算符 - 循环的介绍：while循环及其重复任务的使用 - **讲座5**：列表和for循环 - 列表的创建、索引、切片和基本列表方法 - for循环的介绍及其在列表迭代中的应用 - **讲座6**：集合和循环 - 集合的创建和方法 - 应用for循环于集合及其他数据结构 - **讲座7**：元组和字典 - 元组的创建和属性概述 - 字典的创建、访问值和基本字典方法 - **讲座8**：Python中的函数 - 理解和使用内置函数 - 定义自定义函数、参数和返回值 - **讲座9**：模块和库 - Python模块和库的介绍 - 使用数学模块和理解Python包 - 使用PIP管理Python库 - **讲座10**：字符串操作和文件处理 - 字符串操作与格式化 - 使用Google Colab文件系统进行读写文件 - 实践项目：创建一个简单的Python项目来展示对Python基础的理解 - **生成性AI介绍（讲座11-13）** - **讲座11-12**：文本生成和大型语言模型（LLMs） - 文本生成工具和像ChatGPT、Gemini、Claude等LLMs的概述 - 使用OpenAI Playground和Google AI Studio进行文本生成的实践练习 - 不同AI工具输出结果的实际比较 - **讲座13**：基于AI的代码生成和提示工程 - 使用ChatGPT和Claude的AI代码生成介绍 - 理解Cursor IDE以进行AI辅助编码 - 实践项目：使用AI生成的代码构建一个简单的网页 - **高级生成性AI概念（讲座14-16）** - **讲座14**：图像生成和本地运行LLMs - 图像生成工具（如DALL-E、Midjourney和Stable Diffusion）的概述 - 实践练习：使用runwayML生成和动画图像 - 使用Ollama和LMStudio本地运行开源LLMs - **讲座15**：检索增强生成（RAG） - 通过RAG技术使用LLMs与自定义数据 - 介绍嵌入和向量存储（如chromaDB、qdrant） - 实践练习：构建RAG管道以处理和存储qdrant云中的PDF - **讲座16**：构建真实的AI项目 - 介绍Langchain和LlamaIndex - 实践项目：创建一个基于RAG的问题回答系统网页 - 探索开源AI生态系统以及继续学习的下一步 课程特点： - 实践练习：每节讲座包括Python编码练习、测验和实践项目 - 实践问题：聚焦于现实场景以帮助巩固概念 - Python编码练习：旨在应用Python基础知识构建有意义的应用 完成课程后，学习者将全面掌握Python编程，并获得生成性AI的实践经验，使其能够构建基于AI的项目。
Here's the updated course description including practice questions and a Python coding exercise:Course Description:This 16-lecture course is designed to provide a solid foundation in Python programming and an introduction to Generative AI. Tailored for beginners, the course includes both theoretical lessons and hands-on projects to ensure that learners can apply their knowledge in real-world scenarios. The entire course follows a storytelling format for beginners, offering an immersive experience through recorded class sessions.Course Structure:Lecture 1: Introduction to Generative AI and PythonOverview of the course structure and objectives.Introduction to Python and its importance in AI.Overview of Generative AI, including its applications and relevance in today's world.Python Fundamentals (Lectures 2-10)Lecture 2: Introduction to Python BasicsOverview of programming and Python as a language.Setting up and using Google Colab for coding.Exploring GitHub for code storage and collaboration.Basic syntax in Python: print statements, comments.Lecture 3: Variables and Data TypesUnderstanding variables and their role in programming.Exploring different data types: integers, floats, strings.Simple input and output operations using input() and print() functions.Lecture 4: Control StructuresConditional statements: if, elif, else.Comparison and logical operators.Introduction to loops: while loops and their use in repetitive tasks.Lecture 5: Lists and For LoopsLists: creation, indexing, slicing, and basic list methods.Introduction to for loops and their applications in iterating through lists.Lecture 6: Sets and LoopsWorking with sets: creation and methods.Continuation of for loops, applied to sets and other data structures.Lecture 7: Tuples and DictionariesOverview of tuples: creation and properties.Working with dictionaries: creation, accessing values, and basic dictionary methods.Lecture 8: Functions in PythonUnderstanding and using built-in functions.Defining custom functions, parameters, and return values.Lecture 9: Modules and LibrariesIntroduction to Python modules and libraries.Using the math module and understanding Python packages.Introduction to PIP for managing Python libraries.Lecture 10: String Operations and File HandlingString operations and formatting.Reading from and writing to files using Google Colab's file system.Hands-on project: Create a simple Python project to demonstrate understanding of Python fundamentals.Introduction to Generative AI (Lectures 11-13)Lecture 11-12: Text Generation and LLMsOverview of text generation tools and Large Language Models (LLMs) like ChatGPT, Gemini, and Claude.Hands-on exercises using OpenAI Playground and Google AI Studio for text generation.Practical comparison of outputs from different AI tools.Lecture 13: AI-driven Code Generation and Prompt EngineeringIntroduction to AI-based code generation using tools like ChatGPT and Claude.Understanding Cursor IDE for AI-assisted coding.Practical project: Build a simple web page using AI-generated code.Advanced Generative AI Concepts (Lectures 14-16)Lecture 14: Image Generation and Running LLMs LocallyOverview of image generation tools such as DALL-E, Midjourney, and Stable Diffusion.Practical exercise: Generating and animating images using runwayML.Running open-source LLMs locally using tools like Ollama and LMStudio.Lecture 15: Retrieval Augmented Generation (RAG)Using LLMs with custom data through RAG techniques.Introduction to embeddings and vector stores (chromaDB, qdrant).Practical exercise: Building a RAG pipeline to process and store PDFs in qdrant cloud.Lecture 16: Building Real AI ProjectsIntroduction to Langchain and LlamaIndex.Hands-on project: Create a RAG-based question-answering system on a webpage.Exploring the open-source AI ecosystem and next steps for continued learning.Course Features:Hands-on Practice: Each lecture includes Python coding exercises, quizzes, and practical projects.Practice Questions: Focused on real-world scenarios to help reinforce concepts.Python Coding Exercise: Aimed at applying Python fundamentals to build meaningful applications.By the end of the course, learners will have gained a thorough understanding of Python programming and practical experience with Generative AI, enabling them to build AI-driven projects.
