Skip to main content

AI Tools and Learning Models

We saw the fundamentals and applications of AI. One of the core tasks of AI is learning.

Intelligent Agents​

In AI, we solve problems by creating an actor that can gather data from its environment, make decisions, and take actions to acheive goals. This actor is called an Intelligent Agent.

Agents may also learn and have access to knowledge bases.

Actions taken by an agent may be awarded or punished. Awards make an agent reach its goal. Thus the number one motive of an agent is reaching the goal itself.

Classification and Prediction​

Different goals require different processes. The two most popular AI task types are: classification and prediction.

Classification​

Classification is the process of identifying the category or class of an object based on its features. For example, labeling an email as spam or not spam, or identifying an image as a cat.

Prediction​

Prediction is the process of estimating future values or outcomes based on historical data. For example, predicting stock prices, weather conditions, or customer behavior. If a customer in a standard supermarket buys organic milk, the same customer is more likely to buy organic yoghurt than the average customer.

Learning Models​

AI learning models are algorithms or computational systems that learn patterns from data and use those patterns to make predictions, decisions, or generate outputs.

Popular types are:

  • Supervised Learning: is based on labeled data and inferring functions from training data.
  • Unsupervised Learning: is based on unlabeled data and finding hidden patterns or structures in the data.