Introduction to artificial intelligence

What is Artificial Intelligence?

Artificial Intelligence (often abbreviated as AI) is the intelligence acquired by machines in resemblance to human intelligence.

In the general case, a machine is not intelligent, or it can not do stuff like ‘thinking’, ‘learning’, ‘solving a problem’, ‘error finding’. AI is the science of making intelligent machines that work in accordance with some computer programs. Such machines that acquire intelligence, mimic functions associated with human brains such as “problem-solving” and “learning”. There is an endless number of applications of AI in today’s world. Some of the most common applications include “Expert systems”, “Natural Language Processing” and “speech recognition”. The machines are preprogrammed to acquire intelligence. The programming approach used in this field is specifically called AI programming.

AI programming focuses on three cognitive skills: learning, reasoning, and self-correction.

Learning process –


Like us humans, an AI application needs to learn a specific task before doing it. Our brain collects information about any event and makes use of that information to make decisions when the same event happens later. In the same way, a computer program, or a problem, solving algorithm produces a model that should be able to think from data input.


Reasoning and self-correction –


Reasoning and self-correction are the outcomes of the learning process where the machine decides how to respond to a particular action without any human intervention.

Note: Machine learning is a subset of Artificial Intelligence that includes algorithms that improve themselves with past experiences.


Components of Artificial Intelligence –

  • Machine Learning: Machine Learning teaches a machine how to make inferences and decisions based on past experience. It identifies patterns, analyses past data to infer the meaning of these data points to reach a possible conclusion without having to involve human experience. This automation to reach conclusions by evaluating data saves human time for businesses and helps them make better decisions.
  • Deep Learning: Deep Learning is a Machine Learning technique. It teaches a machine to process inputs through layers in order to classify, infer and predict the outcome. In deep learning, a computer model learns to perform classification tasks from images, sound, or text. The Models are trained by using a large set of labeled data and neural network architectures that contain many layers.
  • Neural Networks: Neural Networks work on similar principles as Human Neural cells. They are a series of algorithms that captures the relationship between various underlying variables and processes the data as a human brain does. An Artificial Neural Network (ANN) or Simulated Neural Network (SNN), is an interconnected group of natural or artificial neurons that uses a mathematical or computational model for information processing based on a connectionist approach to computation. In most cases, an Artificial Neural Network is an adaptive system that changes its structure based on external or internal information that flows through the network.
  • Natural Language Processing: Natural language processing (NLP) is a subfield of linguistics, computer science, and artificial intelligence concerned with the interactions between computers and human language, in particular how to program computers to process and analyze large amounts of natural language data. NLP is a science of reading, understanding, interpreting a language by a machine. Once a machine understands what the user intends to communicate, it responds accordingly.
  • Computer Vision: Computer vision algorithms try to understand an image by breaking down an image and studying different parts of the objects. This helps the machine classify and learn from a set of images, to make a better output decision based on previous observations.
  • Cognitive Computing: Cognitive computing algorithms try to mimic a human brain by analyzing text/speech/images/objects in a manner that a human does and tries to give the desired output.


Applications of AI –

  • AI in Healthcare Industry:

    The applications of AI are infinite. Expert systems are used in the healthcare industry to tell the patients the exact problem depending on the symptoms, balancing doses of drugs, and in some cases to handle surgical processes.

  • AI in Gaming: Chess is a game of intelligence! There are computers that are able to play chess on their own. For instance, ‘Deep Blue’ is a computer that is designed and developed by IBM specifically to play chess. It was the first computer to win against a reigning world chess champion Garry Kasparov in 1997.
  • AI in transportation: Another example of Artificial intelligence is a self-driven car or autonomous vehicle or robotic car. The cars are preprogrammed and provided with all the essential data already in order to reach the destination. It is a vehicle that is capable of moving safely in accordance with the surrounding environment without the need of having any human guidance. Apart from this AI is used to manage traffic, predict air flight delays, and making waterways traffic more safe and efficient.
  • Chatbot: A chatbot is a software that is used for an online chat through text or speech instead of any living human agent. A chatbot could be implemented in websites or mobile apps. In some cases, a chatbot can simulate a conversation through the telephone.
  • AI in Robotics: Artificial Intelligence has an important role in Robotics. Usually, general robots are programmed such that they can perform some repetitive task, but with the help of AI, we can create intelligent robots which can perform tasks with their own experiences without pre-programmed. Humanoid Robots are the best examples of AI in robotics, recently the intelligent Humanoid robot named ‘Sophia’ has been developed which can talk and behave like human beings. It should be noted that Sophia is the first-ever robot citizen in the world.
  • AI in Trading: High-Frequency Trading involves the use of complex AI systems to make trading-related decisions at high speeds than any human being, thus resulting in a number of trades per day.
  • AI in education: AI can automate grading, giving educators more time. It can assess students and adapt to their needs, helping them work at their own pace.
  • AI in banking: Chatbots are implemented in banking systems to make their customers aware of services and to handle transactions that don’t require human intervention. AI virtual assistants are being used to improve and cut the costs of compliance with banking regulations. Banking organizations are also using AI to improve their decision-making for loans and to set credit limits and identify investment opportunities.


Programming Languages used in AI development

There are a number of programming languages used in this field, however, there are some languages that are very much popular and suitable. Given below are the 5 most popular programming languages used in AI.

C++: C++ is an object-oriented (supporting multiple programming paradigms) language developed in 1983 by Bjarne Stroustrup. Search Engines use C++ for less response time.

Java: Java is one of the widest used programming languages in the world and also one of the most popular programming languages used in AI. It is easy to implement on different platforms because of its virtual machine technology. Java has many advantages as an AI language, and the most are easy to use, fast debugging, portable, and automatic memory manager. However, it is slower than C++.

LISP: LISP is the oldest AI programming language. It is the second oldest programming language after Fortran.

Python: Python is an AI programming language that has gained huge popularity. The main reasons are the simple syntax, less coding, and a large number of libraries. Simple syntax means you can focus on the core value of programming, thinking, or problem-solving. The libraries include NumPy, SciPy, matplotlib, nltk, SimpleAI. Python is an open-source AI programming language. That’s why it is very much popular among programmers.

While many AI programming languages use punctuation, Python uses English keywords. It’s simple and designed to be readable. It has only a few keywords and has an easy and clearly defined syntax.

Python supports multiple programming paradigms, dynamic type checking, automatic garbage collection, and can be integrated with C, C++, and many other languages.

Prolog: Prolog is another AI programming language and is one of the oldest ones. It stands for “Programming in logic.” The language is based on a few basic mechanisms like pattern matching and automatic backtracking. It was made in the 1970s by a French computer scientist named Alain Colmerauer.