Title | ||
---|---|---|
Analysis and Improvement of Neural Network Robustness for On-Board Satellite Image Processing |
Abstract | ||
---|---|---|
The topic of this work, a joint scientific program merging the CEA, the IMAG, the CNES (France) and the Naval Research Laboratories (USA), is the evaluation of connectionist techniques for on-board signal and image processing applications in radiative environments (e.g.: space). The objective is to define methods which improve the robustness with respect to radiations of electronic neural systems applied to artificial perception. Theoretical and simulation results are compared to two kinds of experiments: ground tests, performed in France and in the United States on electronic components and boards, an experiment on a neural artificial vision application embedded in a satellite (launch expected in July 1997). In this paper, we describe the first results of our work: after having verified on a natural texture classification application that training a neural network in noisy conditions leads to a significant improvement of robustness, we propose an interpretation of this phenomenon and suggest the use of simple activation functions, compatible with robustness. |
Year | DOI | Venue |
---|---|---|
1997 | 10.1007/BFb0020316 | ICANN |
Keywords | Field | DocType |
neural network robustness,on-board satellite image,activation function,neural network,signal and image processing | Satellite,Computer science,Activation function,Image processing,Robustness (computer science),Artificial intelligence,Electronic component,Artificial neural network,Synaptic weight,Machine learning,Connectionism | Conference |
ISBN | Citations | PageRank |
3-540-63631-5 | 1 | 0.37 |
References | Authors | |
3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jean-Denis Muller | 1 | 3 | 1.82 |
P. Cheynet | 2 | 15 | 2.07 |
Raoul Velazco | 3 | 124 | 19.48 |