University of LiègeULgFaculty of EngineeringFacSALibrary News   
Nicolas Vecoven - Publications ORBI
Vecoven, N., Ernst, D., Wehenkel, A., & Drion, G. (2019). Introducing neuromodulation in deep neural networks to learn adaptive behaviours. Eprint/Working paper retrieved from https://arxiv.org/abs/1812.09113.
In this paper, we propose a new deep neural network architecture, called NMD net, that has been specifically designed to learn adaptive behaviours. This architecture exploits a biological mechanism called ...
Vecoven, N., Begon, J.-M., Huynh-Thu, V. A., & Geurts, P. (2017). Nets versus trees for feature ranking and gene network inference. Eprint/Working paper retrieved from http://orbi.ulg.ac.be/handle/2268/231719.
We propose to tackle the challenging problem of gene regulatory network inference, using variable importance measures derived from artifi cial neural networks (ANN). When combined with a L1-regularized ...