Artificial Intelligence is concerned with “how to make computers do things at which, at the moment, people are better.”

路径规划算法(一)：Dijkstra 和 A*

Dijkstra’s algorithm finds the shortest path to each of the other nodes starting from one of the nodes.

Structured English

Identify the source node (S) where the path starts.

Create an empty set called the ShortestPath set.

Create another set called RemainingNodes and put all of the nodes into this including the source node (S).

Create a record that stores:

    node names

    calculated values for the distance to the node from the source node

    the sequence of nodes in the route to the node.

Set the distance value for the source node S to be 0.

Set the distance value for all other nodes to be INFINITY where this is to be set as a large value greater than any value that will be calculated.

While the ShortestPath set does not include all of the nodes do the following:

    Pick the node (N) from the RemainingNodes set that has the lowest distance value.

    Move this node into the ShortestPath set.

    For each node in the RemainingNodes set that is adjacent to N:

        Calculate a new distance value by adding the value given by the label of the edge connecting the two nodes to the already stored distance for N.

        If this value is less than the value currently stored replace this stored value by the new one that has been calculated.

        If a new value has been stored enter the sequence of nodes used to obtain this value.

A algorithm* - find the best route from one node to just one other node

# Dijkstra
    Calculate a new distance value by adding the value given by the label of the edge
    connecting the two nodes to the already stored distance for N.

# A* 

    Calculate a new distance value by adding the value given by the label of the edge 
    connecting the two nodes to the already stored distance for N.

    Calculate an estimated value for the distance of N from the destination node and 
    add this to the new distance value.

监督学习（supervised learning）的任务是学习一个模型，使模型能够对任意给定的输入，对其相应的输出做出一个好的预测。

即：利用训练数据集学习一个模型，再用模型对测试样本集进行预测。

分类问题（离散）与回归问题（连续）等都是监督学习。

无监督学习（unsupervised learning）为直接对数据进行建模。没有给定事先标记过的训练范例，所用的数据没有属性或标签这一概念。事先不知道输入数据对应的输出结果是什么。

自动对输入的资料进行分类或分群，以寻找数据的模型和规律。

聚类，降维

强化学习是机器学习的另一个领域。它关注的是软件代理如何在一个环境中采取行动以便最大化某种累积的回报。一句话：给定数据，学习如何选择一系列行动，以最大化长期收益。

动态规划、马尔科夫决策

• a computer-based system has a defined task or tasks to perform
• knowledge is acquired through the experience of performing the tasks
• as a result of this experience and the knowledge gained the performance of future tasks is improved.

In unsupervised learning the system has to draw its own conclusions from its experience of the results of the tasks it has performed.

Powerful computer systems having access to massive data banks are regularly used to make decisions based on previous actions recorded.

In supervised learning the system is fed knowledge with associated classification.

A special case of supervised learning is where an expert system is being developed. An expert system always has a focus on a narrowly defined domain of knowledge.

Reinforcement learning has some features similar to unsupervised learning and other features similar to supervised learning.

• An agent is learning how best to perform in an environment.
• The environment has many defined states.
• At each step the agent takes an action.
• An agent has a policy that guides its actions.
• The policy is influenced by the recorded history and the knowledge of the current state of the environment.
• An action changes the environment to a new state.
• The agent receives a reward following an action which is a measure of how effective the action was in relation to the achievement of the overall goal.
• The policy will guide the agent in deciding whether the next action should be exploiting knowledge already known or exploring a new avenue.

In summary, the aim is to maximise the reward values by improving the quality of the policy. It is a trial-and-error search for optimum performance. It requires many repeated attempts at the same problem.

神经网络入门

Artificial neural networks should be considered as a foundation for artificial intelligence systems.

With the increasing computing power now available, artificial neural networks are being introduced with large numbers of hidden layers which are attempting to achieve something similar. These are known as Deep Learning systems.