Activation functions and what are it uses in a Neural Network Model

Activation functions are really important for an Artificial Neural Network to learn and make sense of something really complicated and Non-linear complex functional mappings between the inputs and response variable. They introduce non-linear properties to our Network. Their main purpose is to convert an input signal of a node in an ANN to an output signal. That output signal now is used as an input in the next layer in the stack.
we need to apply an activation function f(x) so as to make the network more powerful and add the ability to it to learn something complex and complicated form data and represent non-linear complex arbitrary functional mappings between inputs and outputs. Hence using a non-linear Activation we are able to generate non-linear mappings from inputs to outputs.
Also, another important feature of an Activation function is that it should be differentiable. We need it to be this way so as to perform backpropagation optimization strategy while propagating backwards in the network to compute gradients of Error(loss) with respect to Weights and then accordingly optimize weights using Gradient descend or any other Optimization technique to reduce Error.

Most popular types of Activation functions:

Sigmoid or Logistic - Predict value in between 0 to 1. Returns f(x) = 1 / (1 + exp(-x))

TanH (Hyperbolic Tangent) - Predict value in between -1 to 1. Returns f(x) = tanh(x)

Read More

Introduction of the perception/neuron

Before we jump straight into neural networks we need to understand the individual components first such as a single neuron.
Artificial neural networks (ANN) actually have a basis in biology so we're going to see how we can attempt to mimic biological neurons of an artificial neuron (otherwise known as the perception) and then once we go through the process of how a simple perception works will go ahead and show you how you can represent that mathematically

Below let's see the biological neuron such as a brain cell

so the biological neuron works as in a simplified way through the following manner, basically you have dendrites that feed into the body of cell you can have many dendrites and what happens is electrical signal gets to pass through the dendrites to the body of the cell and then later on a single output or a single electrical signal is passed on down through an axon to, later on, connects to some other neuron and that's the basic idea we have a kind of the as many inputs of electoral signals to the dendrites goes to the body and in a single actual signal output through the axon so the artificial neuron also has inputs outputs so I go in attempt to mimic the biological neurons.

Read More

Machine Learning

What is machine learning?
Machine learning algorithms are algorithms that learn (often predictive) models from data. I.e., instead of formulating “rules” manually, a machine learning algorithm will learn the model for you.
in another word, Machine learning is a technique to achieve AI through algorithms trained with data.

There are three ways in which machines learn:

Supervised Learning:
Supervised learning is a method in which the machine learns using labelled data. It is like learning under the guidance of a teacher. The training dataset is like a teacher which is used to train the machine. Model is trained on a pre-defined dataset before it starts making decisions when given new data

Read More

Deep Learning

Deep learning is a subset of machine learning which in turn is a subset of artificial intelligence. Artificial intelligence is a technique that enables a machine to mimic human behaviour. Machine learning is a technique to achieve AI through algorithms trained with data and finally, deep learning is a type of machine learning inspired by the structure of the human brain in terms of deep learning this structure is called an artificial neural network let's understand deep learning better and how it's different from machine learning.

Read More

Machine Learning Algorithms

Deep Learning
Deep learning is a subset of machine learning which in turn is a subset of artificial intelligence. Artificial intelligence is a technique that enables a machine to mimic human behaviour. Machine learning is a technique to achieve AI through algorithms trained with data and finally, deep learning is a type of machine learning inspired by the structure of the human brain in terms of deep learning this structure is called an artificial neural network let's understand deep learning better and how it's different from machine learning. We create a machine that could differentiate between tomatoes and cherries if done using machine learning we'd have to tell the Machine the features based on which the two can be differentiated these features could be the size and the type of stem on them with deep learning, on the other hand, the features are picked out by the neural network without human intervention, of course, that kind of independence comes at the cost of having a much higher volume of data to train our machine.

Read More