Derive the perceptron training rule and gradient descent training rule for a single unit with output , where = 0 + 11 + 121 + + + 2. What are the advantages of using gradient descent training rule for training neural networks over the perceptron training rule?

Derive the perceptron training rule and gradient descent training rule for a single unit with output o, where o wo wi wiai + wntn twn. What are the advantages of using gradient descent training rule for training neural networks over the perceptron training rule