Fundamentals of Artificial Intelligence

Fundamentals of Artificial Intelligence

 What is Artificial Intelligence?

Artificial Intelligence is a branch of computer science that deals with the development of methods that allow computers to learn without explicit programming.

Artificial Intelligence is a way of making a digital brain by teaching computers different methods without human interference. In Artificial Intelligence computers learn themselves on the basis of prior experience and learning.

Classical AI and Today's AI:

 In previous times, AI was used manually or with human intervention. A person used to find a problem and solution by himself, then train the computer after setting rules and solutions related to that particular problem.

Today's AI reduced the human effort and hard work. Nowadays, a person has to ask the problem only, AI gives all possible solutions related to that problem.

Goal of AI:

The goal of AI is to perform tasks as humans can do.

For example:

Making decisions and judge etc.

Value Creation by 2030:

The McKinsey Global Institute has predicted substantial value creation of $13 trillion through AI by 2030. This projection is based on AI's potential to revolutionize numerous sectors, such as healthcare, manufacturing, and finance. AI is expected to contribute significantly to economic growth and efficiency in various industries, creating value in the trillions of dollars.

How many types of AI and what are they?

There are three types of Artificial Intelligence on the basis of capabilities.

1. Artificial Narrow Intelligence

2. Artificial General Intelligence

3. Artificial Super intelligence

Artificial Narrow Intelligence:

ANI is also known as Shallow Intelligence. In this type, specific tasks are taught to the computer. 

ANI is commonly used by people for different tasks nowadays and it is continuously enhancing with time.

For example:

Chat GPT, google bard etc. are some  practical examples of ANI.

Artificial General Intelligence and Artificial Super intelligence :

AGI and ASI will be used to perform multiple tasks, but both types do not exist in today’s world but AGI is said to happen in three decades from now.

Example:

One of the best example to understand AGI is the upcoming QSTAR technology of making key which will be able to decode the cipher information.

Popular way to do AI are applying Machine learning and Deep learning.

Machine learning:

In ML, there is no need to instruct computers, data is given to the system and according to prior experience and data, rules are made to apply further.

Deep learning:

Study of neural networks is called deep learning. DL is the study of doing ML with neural networks. In 2012, Neural Networks made up of basic and fundamental mathematical functions like addition, subtraction, multiplication and division etc. these networks are like neurons in the human brain to make a digital brain.

What is the relation between AI, ML and DL?

DL is a subset of ML and ML is a subset of AI. 

ML ⊆ AI and DL ⊆ ML.

What is algorithm?

Most common used term in AI : Algorithms are like step-by-step instructions or rules that tell a computer what to do. They help solve problems or perform tasks by breaking them down into smaller, manageable steps. Just like a recipe guides you in cooking, algorithms guide computers in processing information and making decisions.

Define data and how many types of data are there in Artificial Intelligence?

Data is define as information or facts that are collected, stored, and processed by computers. It can be in various forms such as numbers, text, images, or even sounds. Data is the raw material that computers use to perform tasks, make calculations, and generate insights. It's essentially the building block of information in the digital world.

There are four types of data in AI:

1. Labelled Data

2. Unlabeled Data

3. Structured Data

4. Unstructured Data

Labelled Data:

Data having particular names, is called labelled data.

For example:

Every person or animal has its own particular name like cat, dog etc.

Unlabeled Data:

Data without their specific names, is called unlabeled data.

For example:

If there are random animals but without having their names, for computers, this type of data will be categorized as unlabeled data.

Structured data:

Data in the form of a table, is called structured data. 

For example:

Monthly household, annual GDP of a country on excel sheet etc.

Unstructured Data:

All data which is not in the form of a table, is called unstructured data. It can be in the form of text, image, audio or video etc.

How many types of ANI w.r.t functionality are there?

There are three types of ANI w.r.t functionality

1. Supervised Learning

2. Unsupervised learning

3. Reinforcement

Supervised learning:

In Supervised Learning, only labelled data is used.

In this learning method, the computer is taught by using labelled data (telling names of things) several times, then asking the computer, whether it is a particular thing or not, and the computer will give the correct answer.

Mode of Supervised Learning:

AI Supervised Learning deals with two mode;

● Training mode (for updation)

● Inference mode (for Prediction)

If training is happening, the system will update but there will be no prediction and vice versa.

Both tasks/modes can not perform together.

Unsupervised Learning:

In unsupervised learning, unlabeled data is used.

In this learning, unlabeled data is given to the computer and then the system will make groups according to different attributes like same shape, size, color etc.

Reinforcement:

This learning is based on trial and error method, system is given a specific task, it will perform it once, then again same task will be given to the system, it will perform it in a better way than previous, after several times, system will be able to find out the most optimized way to do that task. This learning method is known as reinforcement.

• All we have discussed above is normally related to Discriminative AI:

Discriminative AI 

It is type of artificial intelligence that focuses on learning to distinguish between different categories or classes in data. It's often used in tasks such as classification, where the AI learns to identify patterns or features that differentiate one class from another. Unlike generative AI, which aims to create new data similar to existing examples, discriminative AI aims to make decisions based on existing data patterns.

Read also about Machine learning and Deep Learning