Explaining Machine Learning to My Grandma

In order to do this, I won’t get too technical, but I will get in-depth into the topic and explain it in simple terms

What is Machine Learning?

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it learn for themselves.

Similar to humans, machine learning allows machines to learn from past experience to solve problems in the future.

How exactly do machines learn?

Machine learning algorithms learn from data to solve problems that are too complex to solve with conventional programming, there’s a lot of math and algorithms involved to help produce the desired results.

Machine learning uses many techniques some of them are :

• Supervised learning - which trains a model/ on known input and output data so that it can predict future outputs.
• Unsupervised learning - which finds hidden patterns or intrinsic structures in input data.
• Semi-supervised machine learning - which falls somewhere in between supervised and unsupervised learning, since they use both labeled and unlabeled data for training
• Reinforcement machine learning - which interacts with its environment by producing actions and discovers errors or rewards.

Neural Networks - Computer like a Brain!

Neural networks are the most popular way to get a computer to mimic a human brain.

Technology and the brain are very closely related in these days. Modern computer applications take into account the features of human brains to solve a problem.
A human brain functions through a network of neurons — or nerve cells — that interact with each other to communicate and process information based on which we see, hear, move, think, make decisions and generally function. The central nervous system and its network of neurons are at the heart of all the activity that happens in the body.

The Neural Network is constructed from 3 type of layers:

• Input layer — initial data for the neural network.
• Hidden layers — intermediate layer between input and output layer and place where all the computation is done.
• Output layer — produce the result for given inputs. Each layer influences the next Deep learning is the name we use for “stacked neural networks”; that is, networks composed of several layers.

There are several kinds of artificial neural networks (ANN), some of them are:

• Feedforward Neural Network (Artificial Neuron) - One of the simplest form of ANN.
• Convolutional Neural Network (CNN) - are applied in techniques like signal processing and image classification technique.
• Recurrent Neural Network (RNN),Long Short Term Memory (LSTM) - found in text to speech (TTS) conversion models.
• Modular Neural Network - have a collection of different networks working independently and contributing towards the output.

Why is machine learning important?

The importance of Machine Learning is deep-rooted in our day to day lives over the past few years, that we fail to identify them, like :

• The heavily hyped, self-driving cars? The essence of machine learning.
• Online recommendation offers such as those from Amazon and Netflix? Machine learning applications for everyday life.

Moving forward the application of Machine Learning is going to increase and as the data becomes more and more available, computational processing becomes cheaper and data storage become even more affordable, the ability to produce sound and highly accurate Machine Learning models would also be very conducive.