Perceptron


The Perceptron is inspired by the information processing of a single neural cell called a neuron.

A neuron accepts input signals via its dendrites, which pass the electrical signal down to the cell body.

In a similar way, the Perceptron receives input signals from examples of training data that we weight and combined in a linear equation called the activation.

$activation = sum(weight_i * x_i) + bias$

The activation is then transformed into an output value or prediction using a transfer function, such as the step transfer function.

$prediction = 1.0$  if activation >= 0.0 else 0.0

In this way, the Perceptron is a classification algorithm for problems with two classes (0 and 1) where a linear equation (like or hyperplane) can be used to separate the two classes.

It is closely related to linear regression and logistic regression that make predictions in a similar way (e.g. a weighted sum of inputs).

The weights of the Perceptron algorithm must be estimated from your training data using stochastic gradient descent.

A perceptron model, in Machine Learning, is a supervised learning algorithm of binary classifiers. A single neuron, the perceptron model detects whether any function is an input or not and classifies them in either of the classes.

Representing a biological neuron in the human brain, the perceptron model or simply a perceptron acts as an artificial neuron that performs human-like brain functions. A linear ML algorithm, the perceptron conducts binary classification or two-class categorization and enables neurons to learn and register information procured from the inputs.

Invented by Frank Rosenblatt in 1957, the perceptron model is a vital element of Machine Learning as ML is recognized for its classification purposes and mechanism.

There are 4 constituents of a perceptron model. They are as follows-

Input values
Weights and bias
Net sum
Activation function



The perceptron model enables machines to automatically learn coefficients of weight which helps in classifying the inputs. Also recognized as the Linear Binary Classifier, the perceptron model is extremely efficient and helpful in arranging the input data and classifying the same in different classes.

There are 2 types of perceptron models-

Single Layer Perceptron- The Single Layer perceptron is defined by its ability to linearly classify inputs. This means that this kind of model only utilizes a single hyperplane line and classifies the inputs as per the learned weights beforehand.

Multi-Layer Perceptron- The Multi-Layer Perceptron is defined by its ability to use layers while classifying inputs. This type is a high processing algorithm that allows machines to classify inputs using various more than one layer at the same time.


Comments

Post a Comment

Popular posts from this blog

Concepts in Machine Learning- CST 383 KTU Minor Notes- Dr Binu V P

About Me Syllabus Previous Year Question Papers-Concepts in Machine Learning CST 383 Module 1:  Overview of  Machine Learning Bayesian Formulation Maximum a Posteriori (MAP), a Bayesian method/Maximum Likelihood Estimation (MLE), Module 2: Supervised Learning Supervised Learning,Regression, Perceptron Naive Bayes Classifier Decision Trees-ID3 Module 3: Introduction to Neural Networks Neural Networks and activation functions Multi Layer Neural Networks, back propagation Back-propagation Example Activation Functions Implementation of a two layer XOR network with  sigmoid activation Application of Neural Networks Support Vector Machines ( SVM) Module 4:Unsupervised Learning Similarity Measures Representative-based Clustering(K-means and Expectation-Maximization Algorithms) Hierarchical Clustering-Agglomerative Clustering ( AHC) Dimensionality Reduction-Principal Component Analysis ( PCA) Factor Analysis Linear Discriminant Analysis ( LDA) Module 5: Classification Assessment Cross validati
Read more

Overview of Machine Learning

Image
To solve a problem on a computer, we need an algorithm. An algorithm is a sequence of instructions that should be carried out to transform the input to output. For example, one can devise an algorithm for sorting. The input is a set of numbers and the output is their ordered list. For the same task, there may be various algorithms and we may be interested in finding the most efficient one, requiring the least number of instructions or memory or both. For some tasks, however, we do not have an algorithm—for example,to tell spam emails from legitimate emails. We know what the input is:an email document that in the simplest case is a file of characters. We know what the output should be: a yes/no output indicating whether the message is spam or not. We do not know how to transform the input to the output. What can be considered spam changes in time and from individual to individual.We can easily compile thousands of example messages some of which we know to be spam and what we want is t
Read more

Syllabus Concepts in Machine Learning- CST 383 KTU

Module-1 (Overview of machine learning)  Machine learning paradigms-supervised, semi-supervised, unsupervised, reinforcement learning. Basics of parameter estimation - maximum likelihood estimation(MLE) and maximum a posteriori estimation(MAP). Introduction to Bayesian formulation. Module-2 (Supervised Learning) Regression - Linear regression with one variable, Linear regression with multiple variables, solution using gradient descent algorithm and matrix method, basic idea of overfitting in regression. Linear Methods for Classification- Logistic regression, Perceptron, Naive Bayes, Decision tree algorithm ID3. Module-3 (Neural Networks (NN) and Support Vector Machines (SVM))   NN - Multilayer feed forward network, Activation functions (Sigmoid, ReLU, Tanh), Backpropagation algorithm. SVM - Introduction, Maximum Margin Classification, Mathematics behind Maximum Margin Classification, Maximum Margin linear separators, soft margin SVM classifier, non-linear SVM, Kernels for learn
Read more