Optimization in recurrent neural networks via Kronecker product
Optimization in recurrent neural networks
The group of Prof. Martin Hasler (LANOS - Nonlinear Systems Laboratory) propose a method to optimize the reservoir considering the fact that one can construct a large matrix using Kronecker products of several small-size matrices.
Recurrent neural networks based on reservoir computing are increasingly being used in many applications. Optimization of the topological structure of the reservoir and the internal connection weights for a given task is one of the most important problems in reservoir computing. The group of Prof. Martin Hasler (LANOS - Nonlinear Systems Laboratory) propose a method to optimize the reservoir considering the fact that one can construct a large matrix using Kronecker products of several small-size matrices.
Ali Ajdari Rad et al., Logic Journal of IGPL 18(5):670-685; 2010