Convergent activation dynamics in continuous time networks
Neural Networks
The neural control of fish swimming studied through numerical simulations
Adaptive Behavior - Special issue on computational neuroethology
SIAM Journal on Scientific Computing
Zeitschrift für Angewandte Mathematik und Physik (ZAMP)
SIAM Journal on Scientific Computing
Convex Optimization
Practical Genetic Algorithms with CD-ROM
Practical Genetic Algorithms with CD-ROM
Design of planar articulated mechanisms using branch and bound
Mathematical Programming: Series A and B
Learning state space trajectories in recurrent neural networks
Neural Computation
Fast Optimization Methods for L1 Regularization: A Comparative Study and Two New Approaches
ECML '07 Proceedings of the 18th European conference on Machine Learning
On the usefulness of non-gradient approaches in topology optimization
Structural and Multidisciplinary Optimization
Modeling and optimal design of Neuro-Mechanical Shape Memory Devices
Structural and Multidisciplinary Optimization
Existence, learning, and replication of periodic motions in recurrent neural networks
IEEE Transactions on Neural Networks
Existence and learning of oscillations in recurrent neural networks
IEEE Transactions on Neural Networks
New results on recurrent network training: unifying the algorithms and accelerating convergence
IEEE Transactions on Neural Networks
Oscillatory neural networks for robotic yo-yo control
IEEE Transactions on Neural Networks
Gradient calculations for dynamic recurrent neural networks: a survey
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
In this paper, we consider optimal design of a type of active mechanical systems referred to as neuro-mechanical oscillators (NMOs). The purpose of an NMO is to generate oscillatory motion, and to this end we pose an optimization problem for finding values of certain design parameters such that optimized systems generate desired motions using a minimal amount of energy. A fully nonlinear model of NMOs is presented and a detailed discussion of the design problem and its numerical treatment is given. Two numerical examples are provided to illustrate how NMOs could work and the usefulness of the proposed design methodology.