|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/bio-inspired-artificial-intelligence-algorithms-for-optimization/
课程评论：没有评论
课程名称：生物启发式人工智能算法 概述： 自然界提供了丰富的灵感，可以将生物过程融入技术和计算中。这些过程和模式激发了用于解决现实世界问题的算法的发展，这些算法被称为生物启发式算法。课程将讲授主要和最常用的生物启发式算法的理论和实践实施。学完课程后，学员将掌握构建能应用于自身问题的人工智能解决方案所需的所有工具。课程分为六个部分，涵盖在真实案例中应用的不同算法。 项目内容包括： 1. **遗传算法（GA）**：解决优化问题的一种广泛使用的生物启发式算法，基于生物进化过程。我们将解决航班调度问题，目标是最小化机票价格和在机场的等待时间。 2. **差分进化（DE）**：也受到生物进化的启发，我们将逐步解决菜单创建问题，正确平衡碳水化合物、蛋白质和脂肪的比例。 3. **神经网络（ANN）**：基于生物神经元的工作原理，是解决复杂问题（如聊天机器人、自动翻译、自动驾驶汽车和语音识别）的现代技术。案例研究将涉及图像分类的神经网络创建。 4. **克隆选择算法（CSA）**：基于对抗原的抗体反应优化过程，模拟生物进化。实践中将用于数字识别和数字生成。 5. **粒子群优化（PSO）**：依赖于动物的社会行为，寻求特定问题的最佳解决方案。我们将解决课程表问题，确定上课的最佳时间。 6. **蚁群优化（ACO）**：基于蚂蚁在自然界中寻找食物的概念。案例研究将探讨经典的最短路径选择问题。 通过学习生物启发式算法的直觉和实现，学员将更容易识别在每种场景中最佳应用的技术。课程中所有的代码将使用Python编程语言逐步实现，并通过Google Colab在线开发，无需担心在本地安装库，所有内容都将在Google的GPU上运行。
Nature offers a wide range of inspirations for biological processes to be incorporated into technology and computing. Some of these processes and patterns have been inspiring the development of algorithms that can be used to solve real-world problems. They are called bio-inspired algorithms, whose inspiration in nature allows for applications in various optimization and classification problems.In this course, you will learn the theoretical and mainly the practical implementation of the main and mostly used bio-inspired algorithms! By the end of the course you will have all the tools you need to build artificial intelligence solutions that can be applied to your own problems! The course is divided into six sections that cover different algorithms applied in real-world case studies. See below the projects that will be implemented step by step:Genetic Algorithms (GA): It is one of the most used and well-known bio-inspired algorithm to solve optimization problems. It is based on biological evolution in which populations of individuals evolve over generations through mutation, selection, and crossing over. We will solve the flight schedule problem and the goal is to minimize the price of air line tickets and the time spend waiting at the airport.Differential Evolution (DE): It is also inspired in biological evolution and the case study we will solve step by step is the creation of menus, correctly balancing the amount of carbohydrates, proteins and fats.Neural Networks (ANN): It is based on how biological neurons work and is considered one of the most modern techniques to solve complex problems, such as: chatbots, automatic translators, self driving cars, voice recognition, among many others. The case study will be the creation of a neural network for image classification.Clonal Selection Algorithm (CSA): It is based on the functioning of the optimization of the antibody response against an antigen, resembling the process of biological evolution. These concepts will be used in practice for digit identification and digit generation.Particle Swarm Optimization (PSO): It relies on the social behavior of animals, in which the swarm tries to find the best solution to a specific problem. The problem to be solved will be the timetable: there is a course, people who want to take it and different timetables. In the end, the algorithm will indicate the best times for each class to take the course.Ant Colony Optimization (ACO): It is based on concepts of how ants search for food in nature. The case study will be one of the most classic in the area, which is the choice of the shortest path. Each type of problem requires different techniques for its solution. When you understand the intuition and implementation of bio-inspired algorithms, it is easier to identify which techniques are the best to be applied in each scenario. During the course, all the code will be implemented step by step using the Python programming language! We are going to use Google Colab, so you do not have to worry about installing libraries on your machine, as everything will be developed online using Google's GPUs!
