|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/foundations-of-ai-actions-under-uncertainty/
课程评论：没有评论
**课程概述：人工智能基础：不确定性下的决策** 本课程深入探讨在现实世界普遍存在的“不确定性”问题，并聚焦于人工智能（AI）如何在信息不完整或环境不可预测的情况下做出决策。课程将从不确定性的本质、成因、度量和表示方法入手，强调概率在量化不确定性中的核心作用。 **主要内容：** * **概率论基础：** 学习概率论的基本定理，理解如何用概率来衡量不确定性。 * **贝叶斯定理与贝叶斯网络：** 深入理解贝叶斯定理，并学习如何利用贝叶斯网络来表示条件独立性。课程将展示贝叶斯网络在航空、商业智能、医疗诊断、公共政策等领域的广泛应用。 * **时序不确定性决策：** 在课程后半部分，我们将探讨时间因素与不确定性如何共同影响决策过程，重点研究马尔可夫性质及其应用。 本课程旨在为学员打下坚实的基础，使其能够设计用于处理不确定性情境的程序和概率图模型，是人工智能领域中理解和解决不确定性问题的入门宝典。
"Real world often revolves around uncertainty. Humans have to consider a degree of uncertainty while taking decisions. The same principle applies to Artificial Intelligence too. Uncertainty in artificial intelligence refers to situations where the system lacks complete information or faces unpredictability in its environment. Dealing with uncertainty is a critical aspect of AI, as real-world scenarios are often complex, dynamic, and ambiguous. This course is a primer on designing programs and probabilistic graphical models for taking decisions under uncertainty. This course is all about Uncertainty, causes of uncertainty, representing and measuring Uncertainty and taking decisions in uncertain situations. Probability gives the measurement of uncertainty. We will go through a series of lectures in understanding the foundations of probability theorem. we will be visiting Bayes theorem, Bayesian networks that represent conditional independence. Bayesian Networks has found its place in some of the prominent areas like Aviation industry, Business Intelligence, Medical Diagnosis, public policy etc.In the second half of the course, we will look into the effects of time and uncertainty together on decision making. We will be working on Markov property and its applications. Representing uncertainty and developing computations models that solve uncertainty is a very important area in Artificial Intelligence"
