Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It only takes a minute to sign up.
Sign up to join this community
If by following way single perceptron is made to work like Logistic Regression.
How much correct is it to say that I made perceptron to work as Logistic Regression.
Question came to mind as activation function of perceptron is a step function and learning is not done by back propagation. https://en.wikipedia.org/wiki/Perceptron
Also as the activation function is changed and also back propagation is considered to be done then is it still a perceptron?
It is perfect to say a logistic regression is a single perceptron. Logistic regression would be a specific case of a perceptron. In fact in Andrew Ng's deep learning specialization, an intuition for perceptron is given by beginning with logistic regression.
Back-propagation helps in scaling up when you add several logistic regressions in series (several hidden layers) and parallel (a single hidden layer). Back propagation for a single perceptron will look like gradient descent for logistic regression.
References
