What Is Perceptron?
Table Of Contents:
- What Is A Perceptron?
- Structure Of Perceptron?
- Activation Function For Perceptron.
- Learning Algorithm For Perceptron.
- Single Layer Perceptron.
- Limitations Of Perceptron.
- Multi-Layer Perceptron.
(1) What Is A Perceptron?
- Perceptrons are the building blocks of artificial neural networks (ANNs) and serve as the simplest form of artificial neuron.
- They were introduced by Frank Rosenblatt in the late 1950s and played a crucial role in the development of neural networks.
- Perceptron is a single-layer neural network and a multi-layer perceptron is called Neural Networks.
- Perceptron is a linear classifier (binary). Also, it is used in supervised learning. It helps to classify the given input data. But how the heck it works?
(2) Structure Of Perceptron.
The perceptron consists of 4 parts.
- Input values or One input layer
- Weights and Bias
- Net sum
- Activation Function
Input values or One input layer:
- This is the primary component of Perceptron which accepts the initial data into the system for further processing.
- Each input node contains a real numerical value.
Wight and Bias:
- The weight parameter represents the strength of the connection between units.
- This is another important parameter of Perceptron components.
- Weight is directly proportional to the strength of the associated input neuron in deciding the output.
- Further, Bias can be considered as the line of intercept in a linear equation.
Net Sum:
- To get the output, the neuron sums up all the values it receives through its connections.
- This neuron’s activation is or as a formula y=wx+b
Activation Function:
- These are the final and important components that help to determine whether the neuron will fire or not.
- Activation Function can be considered primarily as a step function.
(3) Activation Function For Perceptron.
- The activation function in a perceptron is typically a step function.
- If the summed value exceeds a threshold (a bias term), the perceptron outputs one value (e.g., 1); otherwise, it outputs another value (e.g., 0).
- The step function allows the perceptron to make binary decisions or perform binary classification tasks.
- This step function or Activation function plays a vital role in ensuring that output is mapped between required values (0,1) or (-1,1).
- It is important to note that the weight of input is indicative of the strength of a node. Similarly, an input’s bias value gives the ability to shift the activation function curve up or down.
(4) How Perceptron Works?
- The perceptron model begins with the multiplication of all input values and their weights, then adds these values together to create the weighted sum.
- Then this weighted sum is applied to the activation function ‘f’ to obtain the desired output.
- This activation function is also known as the step function and is represented by ‘f’.
- Perceptron model works in two important steps as follows:
Step-1:
- In the first step first, multiply all input values with corresponding weight values and then add them to determine the weighted sum.
- Mathematically, we can calculate the weighted sum as follows:
- Add a special term called bias ‘b’ to this weighted sum to improve the model’s performance.
Step-2:
- In the second step, an activation function is applied with the above-mentioned weighted sum, which gives us output either in binary form or a continuous value as follows:
(5) Learning Algorithm For Perceptron.
- Perceptrons can be trained using a learning algorithm called the perceptron learning rule or the delta rule.
- The learning algorithm adjusts the weights of the inputs based on the error between the perceptron’s output and the expected output.
- The adjustment is applied iteratively to minimize the error and improve the perceptron’s performance.
(6) Types of Perceptron Models
- Based on the layers, Perceptron models are divided into two types. These are as follows:
- Single-layer Perceptron Model
- Multi-layer Perceptron Model
(7) Single-layer Perceptron Model
- A single-layer perceptron consists of an input layer and an output layer.
- The input layer receives input features, and each input feature is associated with a weight.
- The output layer consists of one or more perceptrons, where each perceptron receives weighted inputs from the input layer and produces an output.
(8) Limitations Of Single-layer Perceptron Model.
- Single-layer perceptrons have limitations in their ability to solve problems that are not linearly separable.
- Linear separability means that the data points of different classes can be separated by a straight line or a hyperplane.
- If the data is not linearly separable, a single-layer perceptron cannot find a decision boundary to accurately classify the data.
- However, this limitation was addressed with the development of multi-layer perceptrons (MLPs) that introduced hidden layers and non-linear activation functions.
(9) Multi Layer Perceptron Model.
- Multi-layer perceptrons (MLPs) extend the capabilities of single-layer perceptrons by introducing one or more hidden layers between the input and output layers.
- MLPs can learn non-linear mappings and solve more complex problems.
- The introduction of hidden layers and non-linear activation functions enables MLPs to capture and model complex relationships in the data.