Modular Deep Recurrent Neural Network: Application to Quadrotors

Abstract:A modular deep Recurrent Neural Network (RNN) is introduced to facilitate the process of deploying various architectures of RNNs, and to automatically compute derivatives for gradient-based learning methods. The modularity leads to a set of new architectures, one of which includes feedforward inter-layer connections. By adding feedforward inter-layer connections in a multi-layer RNN, it is observed that the capability of the RNN to learn and model high-order dynamics and nonlinearities is significantly improved. The problem of vanishing/exploding gradient in space for a multilayer RNN is also alleviated using feedforward connections. These results are demonstrated using a quadrotor case study, for which a model of the altitude dynamics is learned with our particular network structure, while existing methods are unable to generalize as quickly or at all.

Machine Learning (cs.LG)

arXiv:2609.04339 [cs.LG]

(or arXiv:2609.04339v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.04339 arXiv-issued DOI via DataCite (pending registration)

N. Mohajerin and S. L. Waslander, "Modular deep Recurrent Neural Network: Application to quadrotors," 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), San Diego, CA, USA, 2014, pp. 1374-1379

https://doi.org/10.1109/SMC.2014.6974106 DOI(s) linking to related resources