NEURAL NETWORK VS DEEP LEARNING

Machine learning and Artificial intelligence have come a long way.

In the age of information and data it got its major push and became the talk of the town.

As the time is passing machine learning and Artificial intelligence are becoming more sophisticated and advanced solving the major problems of our time and opening doors into new mysterious world.

But sometimes the two precious jewels of machine learning are used interchangeably and confuse the homo sapiens using it.

So let’s talk about what is the difference between Deep learning and the neural networks.

Before we move on to the difference between neural network and deep learning ,

let me give you an insight of the hierarchy so that you can get the clear picture.

If I consider the neural network a set then I can say that deep learning is the subset of neural network set.

Which later means that no deep learning is possible without neural network.

Which also means that deep learning and neural networks are having conceptual similarities.

To understand the difference first we should know what a basic neural network contains :

1. Input Layer :where the name says it all that input is given here.
2. Hidden Layer : all the processing of the input happens in the hidden layer.
3. Output Layer:it gives the output based on the processed input

THIS is the basic neural network.

So we are finally ready to dive into the differences that neural network and machine learning holds.

Let’s start with definition:

Neural Network

Neural network are the structures of artificial neurons working on the same concept as the neurons in our brain works to find out the valuable information hidden the dataset.

Deep Learning:

Deep learning are the complex structures of artificial neural networks that make a non-linear processing units comprising of multiple layers for feature transformation and extraction.

With definition the bigger picture in the difference of neural network and deep learning can be understood is

STRUCTURE :

neural network’s one layer consist of :

1. neurons : neuron is a mathematical function which is designed to imitate the functioning of a biological neuron. It computes the weighted average of the data input and passes the information through a nonlinear function, known as “ The activation function”.
2. Learning rate: Learning rate decides how quickly or slowly you want to update the weight (parameter) values of the model.
3. Connection and weights: As the name suggests, connections connect a neuron in one layer to another neuron in the same layer or another layer. Each connection has a weight value linked to it. Here, a weight represents the strength of the connection between the units. The aim is to reduce the weight value to decrease the possibilities of loss (error).
4. Propagation function :Two propagation functions work in a Neural Network: forward propagation that delivers the “predicted value” and backward propagation that delivers the “error value.”

comparison of human brain neuron and artificial neuron

a single neuron

artificial neural network

DEEP LEARNING neural networks contains what neural network structure contains but they are also dependent on machine configuration as they need heavy computation,

so here are some hardware configuration which are required for deep learning:

Processors

The GPU required for Deep Learning must be determined according to the number of cores and cost of the processor.

RAM

This is the physical memory and storage. Since Deep Learning algorithms demand greater CPU usage and storage area, the RAM must be huge.

PSU

As the memory demands increase, it becomes crucial to employ a large PSU that can handle massive and complex Deep Learning functions.

SO At the end all it concludes to that the complex neural networks are nothing but the deep learning .

Give a clap if you learned something new in a clear manner in the confused world :D

Thank you :)