A common AI application that we see today is the automatic switching of appliances at home. When you enter a dark room, the sensors in the room detect your presence and turn on the lights. This is an example of non-memory machines.

Enhancing enterprise performance and productivity through AI technology by automating processes or tasks that were previously performed by humans. AI can also process data on a scale that no human can.

Narrow AI, also known as weak AI, focuses on a single task and is incapable of performing beyond its limitations.Narrow AI applications are becoming more common in our daily lives as machine learning and deep learning methods advance.

General AI, also known as "strong AI," is capable of understanding and learning any intellectual task that a human being is capable of.It enables a machine to apply knowledge and skills in a variety of contexts. So far, AI researchers have not been able to achieve strong AI.

Super AI outperforms human intelligence and is capable of performing any task better than a human. Artificial super-intelligence sees AI evolving to be so similar to human sentiments and experiences that it not only understands them but also evokes emotions, needs, beliefs, and desires of its own.

04.

The goal of supervised learning is to connect input and output data. Supervised learning is based on supervision, just like when a student learns something under the supervision of a teacher. Spam filtering is an example of supervised learning. Supervised learning algorithms are further classified into two types: (i)Classification (ii)Regression

The goal of unsupervised learning is to restructure the input data into new features or a group of objects with similar patterns. There is no predetermined outcome in unsupervised learning. The machine attempts to extract useful insights from the massive amount of data. It is further divided into two types of algorithms: (i)Clustering (ii)Association

Reinforcement learning is a feedback-based learning method in which a learning agent is rewarded for correct actions and penalized for incorrect ones. With this feedback, the agent automatically learns and improves its performance. In reinforcement learning, the agent interacts with and explores the environment.