An Introductory Study on Perceptron in Deep Learning

Abstract

Artificial Intelligence is one of the fastest growing fields in science and engineering and has a wide variety of applications ranging from the general fields like learning, perception and prediction to specific domains such as writing stories, proving mathematical theorems, driving a bus on a crowded street, diagnosing diseases and playing chess. This paper focuses majorly on the pictorial depiction of all the models which aid in understanding the fundamental working of a perceptron – the building block of a neural network. This paper further explores the concept of perceptron aggregation and the purpose of non-linear activation functions thus shedding light on the introductory concepts of deep learning and how individual perceptron aggregate together to form a working deep learning model