Neural Networks

5(e) The neural network below uses the "winner-takes-it-all learning rule. At some instant t during the network training, inputs to the network and the weights of connections are as shown below. a = 1 Wu = 2 01 = 1 X1 W12 = 2 W13 = 1 az = 2 W21 = 1 W22 = 2 02 = 1 X2 W23 = 2 az = 3 Thus, the instant input vector is a = {d; 22; a3}={1; 2; 3}; the fan-in vector of the weights of connections to the 1st output unit is wi={W11; W12; W13}={2; 2; 1}; the fan-in vector of the weights of connections to the 2nd output unit is W2={W21; W22; W23}={1; 2; 2}; i) Calculate the states of the output units Si and S2 at that instant. [4 marks) 5(e) The neural network below uses the "winner-takes-it-all learning rule. At some instant t during the network training, inputs to the network and the weights of connections are as shown below. a = 1 Wu = 2 01 = 1 X1 W12 = 2 W13 = 1 az = 2 W21 = 1 W22 = 2 02 = 1 X2 W23 = 2 az = 3 Thus, the instant input vector is a = {d; 22; a3}={1; 2; 3}; the fan-in vector of the weights of connections to the 1st output unit is wi={W11; W12; W13}={2; 2; 1}; the fan-in vector of the weights of connections to the 2nd output unit is W2={W21; W22; W23}={1; 2; 2}; i) Calculate the states of the output units Si and S2 at that instant. [4 marks)