Perceptron Learning Algorithm

The algorithm for Perceptron Learning is based on the supervised learning procedure discussed previously. This algorithm can be coded in any programming language, and in the case of this tutorial, Java for the applets.

Algorithm:

1. Initialise weights and threshold.

   Set w_i(t), (0 <= i <= n), to be the weight i at time t, and ø to be the threshold value in the output node. Set w₀ to be -ø, the bias, and x₀ to be always 1.

   Set w_i(0) to small random values, thus initialising the weights and threshold.

2. Present input and desired output

   Present input x₀, x₁, x₂, ..., x_n and desired output d(t)

3. Calculate the actual output

   y(t) = f_h[w₀(t)x₀(t) + w₁(t)x₁(t) + .... + w_n(t)x_n(t)]

4. Adapts weights

   w_i(t+1) = w_i(t) + ñ[d(t) - y(t)]x_i(t) , where 0 <= ñ <= 1 is a positive gain function that controls the adaption rate.

Steps iii. and iv. are repeated until the iteration error is less than a user-specified error threshold or a predetermined number of iterations have been completed.

Please note that the weights only change if an error is made and hence this is only when learning shall occur.

Previous:- Perceptron Learning Theory

Next:- Example 2: Binary Logic Unit