Introduction to AISpace
官网：www.aispace.org
These tools are for learning and exploring concepts in artificial intelligence. They were developed at the Laboratory for Computational Intelligence at the University of British Columbia under direction of Alan Mackworth and David Poole. They are part of the online resources for Artificial Intelligence: Foundations of Computational Agents. If you are teaching or learning about AI, you may use these tools under the terms of use. Feedback is welcome.
这些工具是用来学习和探索人工智能的概念。这套工具是由英国哥伦比亚大学计算智能实验室在Alan Mackworth和David Poole。它们是人工智能在线资源的一部分：计算智能体的基础。如果你正在教授和学习有关AI的知识，则可以根据使用协议使用这些工具。欢迎提供反馈。
Search is an important part of AI; many problems can be cast as the problem of finding a path in a graph. This graph-searching tool is designed to help you learn about different search strategies.
搜索是人工智能的重要组成部分，许多问题都可以看作图中的路径搜索问题，图搜索工具旨在帮助你学习不同的搜索策略。
Constraint satisfaction problems (CSPs) are pervasive in AI problems. A constraint satisfaction problem is the problem of assigning values to variables that satisfy some constraints. This tool lets you investigate arc consistency and domain splitting with backtracking as ways to solve these problems.
约束满足问题（CDPs）在人工智能中普遍存在。约束满足问题是满足一些约束条件的变量赋值问题。这个工具可让你调查弧一致性和使用回溯的域分割作为解决这些问题的方法。
This tool is designed to help you learn another strategy for solving CSPs. This tool demonstrates stochastic local search (various mixes of hill climbing and random moves) that walks through the space of total assignments trying to find an assignment with minimal error.
这个工具旨在帮助你学习求解约束满足问题的另一个策略。这个工具演示随机局部搜索（爬山和随机移动的各种组合），它遍历整个分配的空间，试图找到一个误差最小的分配。
Every representation and reasoning system needs a proof procedure in order to be complete. The purpose of this tool is to illustrate how the process of answer extraction within a knowledge base can be cast as a search problem. The deduction tool uses a language similar to Prolog and demonstrates its goal solving procedures.
每个表示和推理系统都需要一个证明程序才能完整。该工具的目的是阐述如何将知识库中的答案提取过程转换为搜索问题。演绎工具使用类似于 Prolog 的语言并演示其目标求解过程。
Belief networks (also called Bayesian networks or causal networks) are a representation for independence amongst random variables for probabilistic reasoning under uncertainty. The purpose of this tool is to illustrate how probabilities are updated given new evidence in a belief network, and shows the details of how the variable elimination algorithm works.
信念网络（也称为贝叶斯网络或因果网络）是随机变量之间独立性的表示，用于在不确定性下进行概率推理。该工具的目的是说明如何在给定信念网络中的新证据的情况下更新概率，并显示变量消除算法如何工作的详细信息。
Learning is the ability to improve one's behaviour based on experience and represents an important element of computational intelligence. Decision trees are a simple yet successful technique for supervised classification learning. This tool demonstrates how to build a decision tree using a training data set and then use the tree to classify unseen examples in a test data set.
学习是根据经验改善个人行为的能力，是计算智能的重要组成部分。决策树是一种简单而成功的监督分类学习技术。该工具演示了如何使用训练数据集构建决策树，然后使用该树对测试数据集中的未见示例进行分类。
Inspired by neurons and their connections in the brain, neural networks are a representation used in machine learning. After running the back-propagation learning algorithm on a given set of examples, the neural network can be used to predict outcomes for any set of input values.
受神经元及其在大脑中的连接的启发，神经网络是机器学习中使用的一种表示。在给定的一组示例上运行反向传播学习算法后，神经网络可用于预测任何一组输入值的结果。
A STRIPS problem is a planning problem that views the world as a set of variables and actions upon them. A problem is solved when a series of actions can be found that will lead to a Goal assignment of values to variables from a Start assignment. The STRIPS to CSP converter allows for the graphical creation of a STRIPS problem and then the conversion of said problem into a CSP for solving.
STRIPS 问题是一个规划问题，它将世界视为一组变量和对其采取的行动。当可以找到一系列动作，这些动作将导致从 Start 分配中将值分配给变量的 Goal 时，问题就解决了。STRIPS 到 CSP 转换器允许以图形方式创建 STRIPS 问题，然后将所述问题转换为 CSP 以进行求解。
转自www.aispace.org
