Memory and forecasting capacities of nonlinear recurrent networks
Abstract
The notion of memory capacity, originally introduced for echo state and linear networks with independent inputs, is generalized to nonlinear recurrent networks with stationary but dependent inputs. The presence of dependence in the inputs makes natural the introduction of the network forecasting capacity, that measures the possibility of forecasting time series values using network states. Generic bounds for memory and forecasting capacities are formulated in terms of the number of neurons of the nonlinear recurrent network and the autocovariance function or the spectral density of the input. These bounds generalize well-known estimates in the literature to a dependent inputs setup. Finally, for the particular case of linear recurrent networks with independent inputs it is proved that the memory capacity is given by the rank of the associated controllability matrix, a fact that has been for a long time assumed to be true without proof by the community.
- Publication:
-
Physica D Nonlinear Phenomena
- Pub Date:
- December 2020
- DOI:
- 10.1016/j.physd.2020.132721
- arXiv:
- arXiv:2004.11234
- Bibcode:
- 2020PhyD..41432721G
- Keywords:
-
- Memory capacity;
- Forecasting capacity;
- Recurrent neural network;
- Reservoir computing;
- Echo state network (ESN);
- Machine learning;
- Mathematics - Optimization and Control;
- Computer Science - Machine Learning;
- Computer Science - Neural and Evolutionary Computing;
- Mathematics - Statistics Theory;
- Statistics - Machine Learning
- E-Print:
- 27 pages, 1 figure. To appear in Physica D