Types of Layers in Artificial Neural Network

In ANN, there are 3 layers,

1. Input Layer
2. Hidden Layer
3. Output Layer

Something like this-

Now Let’s describe each layer in detail. So the first layer is the Input Layer.

Input Layer-

I think now you may have a question in your mind that What signals are pass through the Input layer?.

So in terms of the human brain, these input signals are your senses. These senses are whatever you can see, hear, smells, or touch. For example, if you touch some hot surface, then suddenly a signal sent to your brain. And that signal is the Input signal in terms of the human brain.

But,

In terms of an artificial neural network, the input layer contains independent variables. So the independent variable 1, independent variable 2, and independent variable n.

The important thing you need to remember is that these independent variables are for one observation. In more simple words, suppose there are different independent variables like a person’s age, salary, and job role. So take all these independent variables for one person or one row.

Another important thing you need to know that, you need to perform some standardization or normalization on these independent variables. It depends upon the scenario. The main purpose of doing standardization or normalization is to make all values in the same range.

Now let’s move on to the next layer and that is-

Output Layer-

So, the next question is What can be the output value?

The answer is the output value can be-

1. Continous( Like price).
2. Binary( in Yes/no form).
3. Categorical variable.

If the output value is categorical then the important thing is, in that case, your output value is not one. It may be more than one output value. As I have shown in the picture.

Next, I will discuss synapses.

Synapses-

Synapses are nothing but the connecting lines between two layers.

In synapses, weights are assigned to each synapse. These weights are crucial for artificial neural networks work. Weights are how neural networks learn. By adjusting the weights neural network decides what signal is important and what signal is not important.

Hidden Layer or Neuron-

So the next question is What Happens inside the neurons?

Inside the neurons, the two main important steps happen-

1. Weighted Sum.
2. Activation Function.

The first step is the weighted sum, which means all of the weights assigned to the synapses are added with input values. Something like that-

[ x1.w1+x2.w2+x3.w3+………………..Xn.Wn]

After calculating the weighted sum, the activation function is applied to this weighted sum. And then the neuron decides whether to send this signal to the next layer or not.

I hope now you have a better understanding of Deep Learning Layers.

Happy Learning!

For learning deep learning basics, read this in-depth and super easy guide on deep learning