4 (a) What is a perceptron? Draw a diagram for a single two-input perceptron. Explain what is meant by linear separability. How many categories can it classify inputs into? Mention any issues involved in using a perceptron to compute logical AND, OR and XOR. (7 marks) (b) Illustrate the single perceptron training algorithm for an OR gate by computing the weight adjustments for the first three epochs in Table 4(b) below. (5 marks) (c) Distinguish between a sigmoid neuron and a perceptron, and outline the difference in the training formula for wi. Why might it be preferable to use sigmoid neurons in a neural network rather than perceptrons? (8 marks) (d) Provide a Python code segment which implements the perceptron training algorithm. (5 marks) Perceptron Training for logical OR Threshold =0.2, learning rate =0.1 Table 4(b)