Artificial Intelligence (AI) and Machine Learning (ML)

Artificial intelligence is the opposite of human intelligence. It suggests that machines can imitate humans in speaking, thinking, learning, planning and understanding.
Artificial intelligence is also called machine intelligence and computer intelligence.

1. Artificial Intelligence

Artificial intelligence is a scientific discipline that encompasses several data science areas ranging from narrow AI to strong AI, including machine learning, deep learning, big data, and data mining.

Weak AI

Narrowed Artificial Intelligence is limited to narrow (specific) areas, like most AI we have around us today (e.g. email spam filters, text-to-speech, speech recognition, self-driving cars, e-payment, Google Maps, text autocorrect, automated translation, chatbots, social media, facial recognition, visual perception, search algorithms, robots, automated investing, NLP - Natural Language Processing, flying drones, IBM's Dr. Watson, Apple's Siri, Microsoft's Cortana, Amazon's Alexa, Netflix's recommendations, Narrow AI is also called Weak AI).
Weak AI: Designed to simulate human intelligence. Strong AI: Designed to copy human intelligence.

Strong AI

Strong artificial intelligence is the type of AI that mimics human intelligence. Strong AI refers to the ability to think, plan, learn and communicate. Strong AI is the theoretical next level of AI: True intelligence. Strong AI is moving toward machines with self-awareness, consciousness and objective thoughts.

2. Machine Learning (ML)

Machine learning is a subfield of artificial intelligence. “Learning machines to imitate human intelligence”

Machine Learning vs. Programming

In the conventional programming Algorithms are used to generate results from data:
Data + algorithms = results

Machine learning creates algorithms from data and results:
Data + Results = Algorithms

Neural Networks (NN)

Neural networks are a programming technique used in machine learning that learns from mistakes. Neural networks are based on the way the human brain works. Neurons send messages to each other. As the neurons (repeatedly) try to solve a problem, they strengthen the connections that lead to success and weaken the connections that lead to failure.

Perceptron

A perceptron is an artificial neuron and the simplest neural network possible. Neural networks are the building blocks of machine learning. The perceptron defines the first step in neural networks. It represents a single neuron with only one input layer and no hidden layers.

The original perceptron was designed to process multiple binary inputs and produce a binary output (0 or 1). The idea was to use different weights to represent the importance of each input and that the sum of the values ​​should be greater than a threshold before deciding yes or no (true or false) (0 or 1).

Imagine a perceptron (in your brain). The perceptron is trying to decide whether you should go to a concert. Is the artist good? Is the weather good? How much weight should these facts have?

Criteria	Input	Weighting
Artist is good	x1 = 0 or 1	w1 = 0.7
The weather is good	x2 = 0 or 1	w2 = 0.6
Friend will come	x3 = 0 or 1	w3 = 0.5
Food is served	x4 = 0 or 1	w4 = 0.3

Neural Networks

Neural networks are multilayer perceptrons. In its simplest form, a neural network consists of:

The first layer: The yellow perceptrons make simple decisions based on the inputs. Each individual decision is sent to the perceptron in the next layer.

The second layer: The blue perceptrons make decisions by weighing the results of the first layer. This layer makes more complex decisions at a more abstract level than the first layer.

Deep neural networks

Deep neural networks consist of multiple hidden layers of neural networks that perform complex operations on huge amounts of data. Each subsequent layer uses the previous layer as input. For example, in optical reading, lower layers are used to detect edges and higher layers are used to detect letters.

The first layer:
The yellow perceptrons make simple decisions based on the inputs. Each individual decision is sent to the perceptron in the next layer.

The second layer:
The blue perceptrons make decisions by weighing the results of the first layer. This layer makes more complex decisions at a more abstract level than the first layer.

The third layer:
Even more complex decisions are made by the green perceptron.

Multi-layered learning (Deep Learning DL)

Deep learning is a subset of machine learning that is responsible for the AI ​​boom of recent years. It is an advanced type of ML that takes on complex tasks such as image recognition.