深度学习简介 Neural Network Goodness of Function Pick the Best Function 前馈神经网络 Tips for Deep Learning 卷积神经网络（Convolutional Neural Network, CNN） 循环神经网络（Recurrent Neural Network, RNN） Keras CNN in Keras RNN in Keras

自动规划概述 经典规划 (Classical Planning) 规划问题 状态空间规划 (State-Space Planning) 规划空间规划 (Plan-Space Planning) 新经典规划 (Neoclassical Planning) 规划图技术 (Planning-Graph Techniques) Planning as {SAT, CSP, ILP, …} 经典规划的扩展 分层任务网规划 不确定规划 非确定规划 概率规划

First-Order Logic Why FOL? Syntax and semantics of FOL Using FOL Knowledge engineering in FOL Inference in FOL Reducing first-order inference to propositional inference Unification (合一) Generalized Modus Ponens（一般化分离规则） Forward and backward chaining Resolution

背景 基础 Markov Processes Markov Reward Process Markov Decision Process Extensions to MDPs (Full Observable) Markov Decision Processes (MDPs) Partial Observable MDPs (POMDPs)

Uncertainty Probability Syntax and Semantics Inference Independence and Bayes’ Rule Bayesian network Graphical models Bayesian networks Inference in Bayesian networks

中国科学技术大学：《人工智能基础》课程教学资源（课件讲稿）Lecture 07 Logical Agents

Games Perfect play（最优策略） minimax decisions α − β Pruning Resource limits and approximate evaluation Games of chance (包含几率因素的游戏) Games of imperfect information

CSP examples Backtracking search for CSPs Problem structure and problem decomposition Local search for CSPs

Best-first Search (最佳优先搜索) Greedy search A* search Local Search Algorithms Hill-climbing search Simulated annealing search Local beam search Genetic algorithms

Problem-solving Agents Searching for Solutions Uninformed Search Strategies