Name
Abstract | ||
|---|---|---|
Models in today's microcontrollers, e.g. engine control units, are realized with a multitude of characteristic curves and look-up tables. The increasing complexity of these models causes an exponential growth of the required calibration memory. Hence, neural networks, e.g. multilayer perceptron networks (MLP), which provide a solution for this problem, become more important for modeling. Usually sigmoid functions are used as membership functions. The calculation of the therefore necessary exponential function is very demanding on low performance microcontrollers. Thus in this paper a modified activation function for the efficient implementation of MLP networks is proposed. Their advantages compared to standard look-up tables are illustrated by the application of an intake manifold model of a combustion engine. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/978-3-642-16530-6_49 | AICI (1) |
Keywords | Field | DocType |
engine control unit,multilayer perceptron network,sigmoid function,exponential growth,modified activation function,membership function,look-up table,mlp network,necessary exponential function,low performance microcontrollers,combustion engine,modified sigmoid activation function,exponential function,activation function,multilayer perceptron,neural network,look up table,nonlinear system identification | Inlet manifold,Exponential function,Computer science,Activation function,Nonlinear system identification,Multilayer perceptron,Artificial intelligence,Artificial neural network,Machine learning,Exponential growth,Sigmoid function | Conference |
Volume | ISSN | ISBN |
6319 | 0302-9743 | 3-642-16529-X |
Citations | PageRank | References |
2 | 0.42 | 3 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tobias Ebert | 1 | 2 | 0.42 |
| Oliver Bänfer | 2 | 2 | 0.76 |
| Oliver Nelles | 3 | 99 | 17.27 |