Artificial intelligence project:Given a training set with 20 records,Define a neural network, use Backpropagation Algorithm to train a model by the given training set, find the predicted value for the testing set

These two data is in 2 CSV file. I cant upload csv so that i have uploded the picture of those fileTesting data file: TestingData csv

No	input1	input2	GroundtruthOutput
21	1.42	0.086	58.1
22	2.51	0.071	78.8
23	3.21	0.107	89.6
24	4.29	0.096	96.5
25	5.24	0.65	97.8

Training data file: TrainingData csv

No	input1	input2	output
1	1.16	0.116	50.2
2	1.35	0.104	59.5
3	1.72	0.078	58.8
4	1.86	0.107	66.2
5	1.97	0.136	65.5
6	2.15	0.082	64.5
7	2.23	0.125	73.6
8	2.48	0.076	76.4
9	2.79	0.122	78.5
10	2.85	0.092	79.2
11	3.07	0.081	81.4
12	3.45	0.068	90.3
13	3.59	0.077	93.1
14	3.8	0.108	98.2
15	3.93	0.128	97.3
16	4.14	0.063	98.1
17	4.46	0.135	97.3
18	4.55	0.07	98.8
19	4.84	0.126	96.9
20	5.03	0.087	98.6

Transcribed Image Text:

function BACK-PROP-LEARNING(examples, network) returns a neural network inputs: examples, a set of examples, each with input vector x and output vector y network, a multilayer network with L layers, weights wi,j, activation function g local variables: A, a vector of errors, indexed by network node repeat for each weight wij in network do wi,ja small random number for each example (x, y) in examples do /* Propagate the inputs forward to compute the outputs */ for each node i in the input layer do di + Xi for 2 to L do for each node j in layer & do in; – Σ; Wi,j di aj ← g(inj) /* Propagate deltas backward from output layer to input layer */ for each node j in the output layer do A[j]g'(inj) × (yj aj) for l L 1 to 1 do for each node i in layer l do Δ[i] =g' (ini) Σ; wi, Δ[j] /* Update every weight in network using deltas */ for each weight wij in network do Wi,j < Wi,j + a x ai x_Δ[j] until some stopping criterion is satisfied return network Figure 18.23 The back-propagation algorithm for learning in multilayer networks. function BACK-PROP-LEARNING(examples, network) returns a neural network inputs: examples, a set of examples, each with input vector x and output vector y network, a multilayer network with L layers, weights wi,j, activation function g local variables: A, a vector of errors, indexed by network node repeat for each weight wij in network do wi,ja small random number for each example (x, y) in examples do /* Propagate the inputs forward to compute the outputs */ for each node i in the input layer do di + Xi for 2 to L do for each node j in layer & do in; – Σ; Wi,j di aj ← g(inj) /* Propagate deltas backward from output layer to input layer */ for each node j in the output layer do A[j]g'(inj) × (yj aj) for l L 1 to 1 do for each node i in layer l do Δ[i] =g' (ini) Σ; wi, Δ[j] /* Update every weight in network using deltas */ for each weight wij in network do Wi,j < Wi,j + a x ai x_Δ[j] until some stopping criterion is satisfied return network Figure 18.23 The back-propagation algorithm for learning in multilayer networks.

Answer rating: 100% (QA)

The backpropagation algorithm is used in the classical feedforward artificial neural network It is the technique still used to train large deep learning network The Backpropagation algorithm is a supe... View the full answer