[ad_1]

## Learn the Basics of Artificial Neural Networks

You may have heard the term Neural Networks used often by AI & ML researchers. But have you ever wondered what it really means?

Read the blog to find out more.

Neural Networks or Artificial Neural Networks are **a subset of machine learning and are at the heart of deep learning algorithms.**

It is a series of algorithms that **endeavors to recognize underlying relationships** in a set of data through a process that mimics the way the human brain operates.

These artificial neural networks are used for **predictive modelling** i.e. predicting event outcomes and to build applications which can learn from a dataset.

Some of the Common examples of Neural Networks include CNNs (Convolutional Neural Networks) and LSTMs (Long Short-Term Memory Network):

**Convolutional neural network**=> Good for image recognition**Long Short-Term memory network**=> Good for Speech Recognition

- It is a mathematical function that models the functioning of a biological neuron.
- It computes the weighted average of its input and passes the sum through a non-linear function called the activation function (such as the sigmoid).

Although training a neural network can be a time-consuming process for many, the process is really simple to understand.

Each neural network contains an Input layer, Hidden Layer/s and an Output layer. The input layer contains nodes which indicate our features which we provide to our ANN while the Output layer contains our predicted output. The number of nodes in Hidden layers will be based on your requirements.

The goal of training any ANN is to **minimize the error between the classification of the incoming data (actual output) and the one made by the neural network (predicted output).**

While training an ANN, **each time you are updating the weights & biases and back-propagating the error.**

The below diagram summarizes the process using 4 simple steps:

- The process of repeated nudging an input of a function by some multiple of the negative gradient is called
**Gradient Descent.** - When there are one or more inputs, you can use Gradient descent for
**optimizing the values of the coefficients by iteratively minimizing the error of the model on your training data**. - A
**learning rate**is used as a scale factor and the coefficients are updated in the direction towards**minimizing the error**. - This process is
**repeated until a minimum sum squared error is achieved or no further improvement is possible.**

- It is an algorithm for supervised learning of an ANN using Gradient Descent.
- Given an ANN and an error function it calculates the gradient of the error function w.r.t. the NN weights.
- Here the partial computations of the gradient from one layer are reused in the computation of the gradient for the previous layer.

- The chain rule expressions give us the derivatives that determine each component in the gradient that helps to minimize the cost of the network by repeatedly stepping downhill.

So here you go folks, you now know the basics of Artificial Neural Networks.

Although we haven’t covered the intricacies involved with creating and building an Artificial Neural Network from scratch, the above should give you an idea about what ANNs are and how they work.

Cheers!

[ad_2]

Source link