Neural Optimization Machine: A Neural Network Approach for Optimization
This addresses optimization problems broadly, including multiobjective cases and applications like additive manufacturing, but appears incremental as it adapts existing neural network methods.
The paper tackles constrained optimization by proposing a neural network approach called Neural Optimization Machine (NOM), which uses backpropagation to solve problems with results showing that computational cost does not significantly increase with design variable dimensions.
A novel neural network (NN) approach is proposed for constrained optimization. The proposed method uses a specially designed NN architecture and training/optimization procedure called Neural Optimization Machine (NOM). The objective functions for the NOM are approximated with NN models. The optimization process is conducted by the neural network's built-in backpropagation algorithm. The NOM solves optimization problems by extending the architecture of the NN objective function model. This is achieved by appropriately designing the NOM's structure, activation function, and loss function. The NN objective function can have arbitrary architectures and activation functions. The application of the NOM is not limited to specific optimization problems, e.g., linear and quadratic programming. It is shown that the increase of dimension of design variables does not increase the computational cost significantly. Then, the NOM is extended for multiobjective optimization. Finally, the NOM is tested using numerical optimization problems and applied for the optimal design of processing parameters in additive manufacturing.