Download presentation
Presentation is loading. Please wait.
Published byRidwan Yuwono Modified over 6 years ago
1
Artificial Neural Networks (ANNs) and the Error Backpropagation Procedure
Prof. Carolina Ruiz Department of Computer Science Worcester Polytechnic Institute
2
A 2-layer feedforward ANN
Input hidden layer output layer -1 -1 -1
3
Error Backpropagation
Out 1 1. Initialize the weights to small random values -1 0.5 0.1 A C -0.2 -0.1 E 0.05 0.3 D B 0.2 0.5
4
Error Backpropagation
Out 1 2. For each of the examples: 2.1. Present example to input layer 2.2. Propagate the example forward -1 0.5 0.1 0.377 A C -0.2 -0.1 E 0.5094 0.05 0.3 D 0.377 B 0.2 0.5
5
Error Backpropagation
Out 1 2. For each of the examples: 2.3. Compute node errors for output layer 2.4. Compute node errors for hidden layer -1 0.025 0.5 0.1 0.377 A C -0.2 -0.1 E 0.5094 0.05 0.3 D 0.377 B 0.2 0.5
6
Error Backpropagation
Out 1 2. For each of the examples: 2.5. Compute and record weight change for each connection -1 0.025 0.5 0.1 0.377 A C -0.2 A->C 0.0000 A->D B->C B->D C->E D->E -0.1 E 0.5094 0.05 0.3 D 0.377 B 0.2 0.5
7
Error Backpropagation
Out 1 3. After processing all examples update weight 4. Repeat process until obtaining “good” weights -1 0.025 0.5 0.1 0.377 A C -0.2 A->C 0.0001 A->D B->C 0.0004 B->D C->E 0.3853 D->E -0.049 -0.1 E 0.5094 0.05 0.3 D 0.377 B 0.2 0.5
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.