Figure P4.1 shows a neural network involving a single hidden neuron, for solving the XOR problem: this network may be viewed as an alternative to that considered in Section 4.5. Show that the network of Fig. P4.1 solves the XOR problem by constucting (a) decision regions, and (b) a truth table for the network. Use the back-propagation algorithm for computing a set of synaptic weights and bias lev els for a neural network structured as in Fig. 4.8 to solve the XOR problem. Assume the use of a logistic function for the nonlinearity +1 +1 -2 Output +1 FIGURE P4.1 Neuron 1 Neuron 3 Neuron 2 Input layer Hidden layer Output layer 1.5 +1 -2 +1 pt +1 +1 0.5 x. -0.5 +1 FIGURE 4.8 (a) Architectura graph of network for solving the XOR problem. (b) Signal- flow graph of the network. Figure P4.1 shows a neural network involving a single hidden neuron, for solving the XOR problem: this network may be viewed as an alternative to that considered in Section 4.5. Show that the network of Fig. P4.1 solves the XOR problem by constucting (a) decision regions, and (b) a truth table for the network. Use the back-propagation algorithm for computing a set of synaptic weights and bias lev els for a neural network structured as in Fig. 4.8 to solve the XOR problem. Assume the use of a logistic function for the nonlinearity +1 +1 -2 Output +1 FIGURE P4.1 Neuron 1 Neuron 3 Neuron 2 Input layer Hidden layer Output layer 1.5 +1 -2 +1 pt +1 +1 0.5 x. -0.5 +1 FIGURE 4.8 (a) Architectura graph of network for solving the XOR problem. (b) Signal- flow graph of the network