[Solved]-Using Concrete Example Explain Concept Supervised Learning Ii Unsupervised Learning Iii R Q37241652

(a) Using a concrete example, explain the concept of i. Supervised learning ii. Unsupervised learning iii. Reinforcement learning. [2 Marks] 2 Marks] [2 Marks] (b) State the major reasons why a multi-layer feedforward neural network is of 3 Marks] (c) We need to train a neural network to learn a function which takes three very strong capability in nonlinear mapping. integers as input, representing weight, fuel capacity and passenger numbers and outputs either “car” or “bus”. The ANN is provided in Figure Q5(c). State why there are four input nodes. i. [1 Mark] ii. Determine the values of x and y? [2 Marks] ii. Deduce whether the network predicts a bus or a car if the input is (10, 12, 2 Marks] iv. Suppose that the input (10, 12, 13) has been mis-categorized by the 13) perceptron, calculate the weight change for the weights in the network in light of this training network, if a learning rate of 0.1 is applied 3 Marks v. Draw the re-trained network. [1 Mark] vi. Using the input (5, 7,7), determine whether the network is over-corrected. [2 Marks] +1- BUS 7X 0.2 -0 1- CAR Figure Q5(c) Page 8 of 9 (d) A feed-forward neural network with one hidden layer in shown in Figure Q5(d). A weight on connection between nodes i and j is denoted by Wij, such as wi3 is the weight on the connection between nodes 1 and 3. The Table Q5(d-1) lists all the weights in the network. w23-3451 Table Q5(d-1) Each of the nodes 3, 4, 5 and 6 uses the following activation function 1 if v 20 t 0 otherwise 0(v) where v denotes the weighted sum of a node. Each of the input nodes (1 and 2) can only receive binary values (either 0 or 1). By showing your working, calculate the output of the network (ys and ys) for each of the input patterns shown in Table Q5(d-2) 5 Marks] Pattern: P P Ps P Node 10 0 1 Node 2:001 1 Table Q5(d-2) Figure Q5(d) Show transcribed image text (a) Using a concrete example, explain the concept of i. Supervised learning ii. Unsupervised learning iii. Reinforcement learning. [2 Marks] 2 Marks] [2 Marks] (b) State the major reasons why a multi-layer feedforward neural network is of 3 Marks] (c) We need to train a neural network to learn a function which takes three very strong capability in nonlinear mapping. integers as input, representing weight, fuel capacity and passenger numbers and outputs either “car” or “bus”. The ANN is provided in Figure Q5(c). State why there are four input nodes. i. [1 Mark] ii. Determine the values of x and y? [2 Marks] ii. Deduce whether the network predicts a bus or a car if the input is (10, 12, 2 Marks] iv. Suppose that the input (10, 12, 13) has been mis-categorized by the 13) perceptron, calculate the weight change for the weights in the network in light of this training network, if a learning rate of 0.1 is applied 3 Marks v. Draw the re-trained network. [1 Mark] vi. Using the input (5, 7,7), determine whether the network is over-corrected. [2 Marks] +1- BUS 7X 0.2 -0 1- CAR Figure Q5(c) Page 8 of 9
(d) A feed-forward neural network with one hidden layer in shown in Figure Q5(d). A weight on connection between nodes i and j is denoted by Wij, such as wi3 is the weight on the connection between nodes 1 and 3. The Table Q5(d-1) lists all the weights in the network. w23-3451 Table Q5(d-1) Each of the nodes 3, 4, 5 and 6 uses the following activation function 1 if v 20 t 0 otherwise 0(v) where v denotes the weighted sum of a node. Each of the input nodes (1 and 2) can only receive binary values (either 0 or 1). By showing your working, calculate the output of the network (ys and ys) for each of the input patterns shown in Table Q5(d-2) 5 Marks] Pattern: P P Ps P Node 10 0 1 Node 2:001 1 Table Q5(d-2) Figure Q5(d)

Expert Answer

---

Answer to (a) Using a concrete example, explain the concept of i. Supervised learning ii. Unsupervised learning iii. Reinforcement… . . .