Unformatted text preview: Dr. Cédric Pradalier Institut für Robotik und Intelligente Systeme Autonomous Systems Lab CLA E 16.1 Tannenstraße 3 8092 Zürich [email protected] www.asl.ethz.ch/people/cedricp Exercise Sheet 3 – Solutions
Problem 1: Neural Network Design Topics: Artificial Neural Networks Select appropriate neural network parameters (number of input, number of output, use of hidden layers, activation functions) for the following applications. Additionally, for each application, describe an example data set that could be used for training the network. (a) An ANN to predict the voltage on a resistor based on its input electric current.
i V This electric circuit is described by a relation V = Ri. In order to learn linear system with single input and single output, a single neuron is necessary: i V (b) An ANN to predict the voltage V1 and V2 at the terminals of two resistors based on their input current i.
i V1 V2 This electric circuit is described by a relation V1 = Ri and V2 = Ri. In order to learn linear system with single input and two output, two linear neurons are necessary: i V1 V2 1 (c) An ANN to predict the electric current i1 and i2 going through two resistors in parallel, based on the voltage V on the circuit terminals.
View Full Document
- Spring '10
- Artificial neural network, neural network, ØÛÓÖ ºÐ, ØÛÓÖ ºÛ Ø¾, ÔÖ ÒØ ´³È