|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/ai-and-combinatorial-optimization-with-meta-heuristics/
课程评论：没有评论
Coursera 课程：AI 和元启发式算法（组合优化）Python 本课程专注于人工智能和元启发式算法的基础概念，并使用 Python 进行实现。该主题目前非常热门，因为这些学习算法可应用于从软件工程到投资银行业务等多个领域，例如识别模式以辅助癌症检测，或预测股票市场波动。 **课程核心内容：** * **路径查找算法：** * 广度优先搜索 (BFS)：介绍 BFS 算法及其在人工智能中的应用。 * 深度优先搜索 (DFS)：讲解 DFS 算法，提供迭代和递归实现，并可视化其在迷宫逃生等问题中的应用。 * A* 搜索算法：讲解 A* 算法，与 Dijkstra 算法进行比较，并介绍启发式函数（如曼哈顿距离和欧几里得距离）。 * **元启发式算法：** * 模拟退火：深入了解模拟退火算法，如何寻找函数极值，以及解决旅行商问题 (TSP)、数独等组合优化问题。 * 遗传算法：探索遗传算法，包括人工进化、自然选择、交叉和变异，并应用于背包问题和 N 皇后问题。 * 粒子群优化 (PSO)：讲解群体智能的概念及粒子群优化算法。 * **游戏与博弈树：** * 博弈树：介绍博弈树的概念及其构建方法。 * Minimax 算法与游戏引擎：讲解 Minimax 算法，分析博弈树的局限性，并介绍 Alpha-Beta 剪枝技术（以国际象棋为例）。 * Tic Tac Toe (井字棋) 与 Minimax：实现井字棋游戏，并运用 Minimax 和 Alpha-Beta 剪枝算法。 * **强化学习：** * 马尔可夫决策过程 (MDP)：介绍强化学习基础，包括价值迭代、策略迭代、探索与利用的权衡，以及多臂老虎机问题。 * Q 学习算法：讲解 Q 学习算法，并将其应用于井字棋学习。 * **Python 编程速成：** * Python 基础：涵盖 Python 编程基础、基本数据结构、内存管理以及面向对象编程 (OOP)。 * NumPy：介绍 NumPy 库。 课程将从基础图算法（BFS, DFS, A\*）开始，然后转向启发式和元启发式算法，涵盖模拟退火、遗传算法和粒子群优化，并通过 N 皇后问题、旅行商问题等实际示例进行实现。最后，课程将深入游戏理论和强化学习，并通过 Python 实现来巩固理论知识。
This course is about the fundamental concepts of artificial intelligence and meta-heuristics with Python. This topic is getting very hot nowadays because these learning algorithms can be used in several fields from software engineering to investment banking. Learning algorithms can recognize patterns which can help detecting cancer for example. We may construct algorithms that can have a very good guess about stock price movement in the market. ### PATHFINDING ALGORITHMS ###Section 1 - Breadth-First Search (BFS)what is breadth-first search algorithmwhy to use graph algorithms in AISection 2 - Depth-First Search (DFS)what is depth-first search algorithmimplementation with iteration and with recursiondepth-first search stack memory visualizationmaze escape applicationSection 3 - A* Search Algorithmwhat is A* search algorithmwhat is the difference between Dijkstra's algorithm and A* searchwhat is a heuristicManhattan distance and Euclidean distance### META-HEURISTICS ###Section 4 - Simulated Annealingwhat is simulated annealinghow to find the extremum of functionshow to solve combinatorial optimization problemstravelling salesman problem (TSP)solving the Sudoku problem with simulated annealingSection 5 - Genetic Algorithmswhat are genetic algorithmsartificial evolution and natural selectioncrossover and mutationsolving the knapsack problem and N queens problemSection 6 - Particle Swarm Optimization (PSO)what is swarm intelligencewhat is the Particle Swarm Optimization algorithm### GAMES AND GAME TREES ###Section 7 - Game Treeswhat are game treeshow to construct game treesSection 8 - Minimax Algorithm and Game Engineswhat is the minimax algorithmwhat is the problem with game trees?using the alpha-beta pruning approachchess problemSection 9 - Tic Tac Toe with MinimaxTic Tac Toe game and its implementationusing minimax algorithmusing alpha-beta pruning algorithm### REINFORCEMENT LEARNING ###Markov Decision Processes (MDPs)reinforcement learning fundamentalsvalue iteration and policy iterationexploration vs exploitation problemmulti-armed bandits problemQ learning algorithmlearning tic tac toe with Q learning ### PYTHON PROGRAMMING CRASH COURSE ###Python programming fundamentalsbasic data structures fundamentals of memory managementobject oriented programming (OOP)NumPyIn the first chapters we are going to talk about the fundamental graph algorithms - breadth-first search (BFS), depth-first search (DFS) and A* search algorithms. Several advanced algorithms can be solved with the help of graphs, so in my opinion these algorithms are crucial.The next chapters are about heuristics and meta-heuristics. We will consider the theory as well as the implementation of simulated annealing, genetic algorithms and particle swarm optimization - with several problems such as the famous N queens problem, travelling salesman problem (TSP) etc.Thanks for joining the course, let's get started!
