Artificial Intelligence, Machine Learning, and Deep Learning Overview

Artificial Intelligence History

The term “Artificial Intelligence” was actually coined by John McCarthy in 1956. In the year 1950s, a handful of scientists in various mathematics, psychology, engineering, engineering, economics and political sciences began to talk about the possibility of creating an artificial brain.

Overview of Artificial Intelligence

Artificial intelligence(AI) is a science and technology based on disciplines such as Computer science, Engineering, Psychology, Biology, Linguistics, and Mathematics.

AI (Artificial intelligence) is combination of following disciplines

Computer science

Psychology

Biology

Engineering

Mathematics

Linguistics

Definition of Artificial Intelligence

AI (Artificial intelligence) is a branch of computer science that aims to create intelligent machines which act like a human.

Artificial Intelligence machine Learning
Artificial Intelligence machine Learning

Or

According to John McCarthy, AI is “The science and engineering of making intelligent machines, especially intelligent computer programs”.

Artificial Intelligence is a way of making a computer, or a software thinks intelligently as intelligent humans think.

Artificial Intelligence machine Learning
Artificial Intelligence(AI), Machine Learning, and Deep Learning 

Machine Learning

Introduction to Machine Learning

Machine Learning is a subset of AI, focusing on the development of machines and algorithms that can access the data and use it to learn for themselves.

Best definition of machine learning in a nutshell by Tom Mitchell is:

“A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E ” by Tom Mitchell

Types of Machine learning

Machine learning algorithms broadly are often categorized as Supervised, Unsupervised, and Reinforcement Machine learning algorithms.

Machine Learning
Machine Learning

Supervised machine Learning algorithm searches for patterns within the value labels that were assigned to data points. With the base of these level data set it make predictions.

Unsupervised Machine Learning No labels are associated with data points, it organized data into a group of clusters.

Reinforcement learning Algorithm that Agent interacts with its environment by producing actions and discovers errors or rewards. After some time, the algorithm changes its strategy to learn better according to past experience.

Limitation of the Machine Learning

MI (Machine Learning) useful only when Data Volume is not too large.

The Second limitation of machine Learning is in Field of feature extraction. When the data Volume is small, Machine Learning algorithms perform that well.

Machine Learning and Deep Learning
Machine Learning and Deep Learning

What is Deep Learning?

Deep learning (DL) is a subset of machine learning in that has Machine capable of learning unsupervised from data that is unstructured or unlabeled. It inspired by biological Neurons also known as Deep Neural Network.

Deep learning is one of the only ways by which we can solve the problem of high dimensionality data and overcome the challenges of feature extraction.


Deep Neural Network

A deep learning model is designed to continually analyze data with a logic structure similar to how a human brain cell would draw conclusions.The deep learning model is inspired by the basic unit of a brain called a neuron.

There are three important things in working of a biological neuron. These things are dendrite, call center, and Axons.

Dendrite:  Dendrites which is used to receive inputs from the environment.

Axons: Axon passed inputs summed on to the next biological neuron.

Cell body: These inputs are summed in the cell body (nucleus).

Brain cell (Neuron)
Brain cell (Neuron)

Perceptron

An artificial neuron is inspired by biological neurons known as Perceptron. The fundamental building block of Deep Learning is the Perceptron which is a single neuron in a Neural Network.

Similarly, there are three important parts in working of a Perceptron.

  Inputs(X): perceptron receives multiple inputs like Dendrite in Biological Neurons.

  Transfer Function (∑): These inputs are summed in the Transfer Function like cell body.

Deep Learning Perceptron
Deep Learning Perceptron

  Activation functions (∫):  Activation functions passed on to the next Perceptron like Axon.


You may also like...

Leave a Reply

Your email address will not be published. Required fields are marked *