Artificial Intelligence

Introduction

AI is a branch of Computer science. The purpose of AI is to create systems that can function intelligently and independently. 

Why is it called Artificial Intelligence? 
Human beings are the creator of these machines, they program them and give them the ability of decision making. Hence, human beings are considered to have real intelligence and this is how artificial intelligence got its name.

Classification of AI

NLP: Natural Language Processing
NN: Neural Networks 
CNN: Convolution Neural Network 
RNN: Recurrent Neural Network 

Explanation of the above flow chart:

AI can be broadly classified into Symbolic Learning and Machine Learning.

1. Symbolic Learning 

Symbolic Learning, as the name suggests, is a symbolic way for us to process information.

1.1 Computer Vision

Humans recognize a scene around them through their eyes which create images of the world. 

Computer vision is a field of artificial intelligence (AI) that enables computers and systems to derive meaningful information from digital images, videos, and other visual inputs, and take actions or make recommendations based on that information.

Image 1 - Human viewing natural scenery

Computers recognize the same using Computer vision

1.2 Robotics

Robots are machines that can move around fluidly like humans and perform tasks done traditionally by human beings.

Image 2 - Robots are an example of Artificial Intelligence in practice

2. Machine Learning

Machine learning works on the principle of pattern recognition. The ability to see patterns and group like objects is called pattern recognition. Human beings can naturally recognize patterns. Machines can do better pattern recognition because they can scan through more data and dimensions of the data.

Image 3 - Pattern recognition puzzle

2.1 Statistical learning

Statistical learning is learning using a set of tools for understanding data.

2.1.1 Speech recognition 

Human beings can speak, listen and communicate through language. Speech recognition refers to a computer interpreting the words spoken by a person and converting them to a format that is understandable by a machine. Depending on the end goal, it is then converted to text or voice or another required format.

Image 4 - Recording and converting sound into a language understandable by AI

2.1.2 NLP (Natural Language Processing)

The Natural Language Processing field is concerned with giving computers the ability to understand the text and spoken words in the same way human beings can.

Image 5 - Different languages used by human beings 

2.2 Deep Learning (NN)

The human brain is a network of neurons and we use these to learn things and store information. If we can replicate the structure and function of the human brain we might be able to get cognitive capabilities in machines. This is a field of neural networks (NN). 

If these networks are more complex and deeper, we use those to learn complex things which are in the field of deep learning. There are different types of deep learning in different machines which are essentially different techniques to replicate what the human brain does.

Image 6 - Human v/s AI brain

2.2.1 CNN (Convolution Neural Network)

If we get the network to scan images from left to right, top to bottom is a Convolution Neural Network (CNN). A CNN is used to recognize objects in a scene. This computer vision and object recognition are accomplished through AI.

CNN uses a computer vision technique called object recognition. Object recognition is used for identifying objects in images or videos.

Image 7 - Convolution Neural Network

2.2.2 RNN (Recurrent neural network)

Humans can remember past memories like what you had for dinner last night. For machines, we can get a neural network to remember a limited past. This is a Recurrent Neural Network (RNN).

Image 8 - Recurrent Neural Network

Conclusion and applications

There are two ways AI can be classified, one is symbolically based and another is data-based. For the data-based side, called machine learning, we need to feed the machine lots of data before we can learn.

For example, if you had lots of data for sales versus profit you can plot that data to see some kind of pattern. If the machine can learn this pattern then it can make predictions based on what it has learned. While one or two or even three dimensions are easy for humans to understand and learn, machines can learn in many more dimensions like even hundreds or thousands. That's why machines can look at lots of high-dimensional data and determine patterns. 

Please leave your comments below.

Image 1 Source: https://previews.123rf.com/images/blasbike/blasbike1510/blasbike151000019/45775486-wandelen-man-klimmer-of-sleepagent-kijken-naar-mooie-uitzicht-in-de-bergen-reizen-in-itali%C3%AB-europa-f.jpg?fj=1

Image 2 Source: https://www.nato.int/docu/review/images/a871f9_1_ehlert_ai.jpg

Image 3 Source: https://i.stack.imgur.com/1vq1V.png

Image 4 Source: https://st2.depositphotos.com/1456491/6782/v/950/depositphotos_67821667-stock-illustration-speak-and-listen.jpg

Image 5 Source: https://www.worthview.com/wp-content/uploads/2015/04/Thank-you-different-languages.jpg

Image 6 Source: https://cdn1.vectorstock.com/i/1000x1000/50/50/human-brain-mind-head-with-artificial-intelligence-vector-21175050.jpg

Image 7 Source: https://editor.analyticsvidhya.com/uploads/25366Convolutional_Neural_Network_to_identify_the_image_of_a_bird.png

Image 8 Source: https://www.researchgate.net/profile/Vidushi-Mishra/publication/324883736/figure/fig2/AS:621644821307392@1525223083712/Recurrent-neural-networkRNN-or-Long-Short-Term-MemoryLSTM-5616.png