Implement a perceptron and train it to recognise the digital letters given in pattern1. Show a training curve and show the depenence on the recognition rate with different levels of noise. The later graph should include error bars. Compare these results with the method you used in the exercise before (or with a lookup table based on the hamming distance).
Write up your project in a short (!) paper that includes a brief decription of the methods used and a discussion of the results.