Reservoir Size, Spectral Radius and Connectivity in Static Classification Problems
نویسندگان
چکیده
Abstract. Reservoir computing is a recent paradigm that has proved to be quite effective given the classical difficulty in training recurrent neural networks. An approach to using reservoir recurrent neural networks has been recently proposed for static problems and in this paper we look at the influence of the reservoir size, spectral radius and connectivity on the classification error in these problems. The main conclusion derived from the performed experiments is that only the size of the reservoir is relevant with the spectral radius and the connectivity of the reservoir not affecting the classification performance.
منابع مشابه
Extending Stability Through Hierarchical Clusters in Echo State Networks
Echo State Networks (ESN) are reservoir networks that satisfy well-established criteria for stability when constructed as feedforward networks. Recent evidence suggests that stability criteria are altered in the presence of reservoir substructures, such as clusters. Understanding how the reservoir architecture affects stability is thus important for the appropriate design of any ESN. To quantit...
متن کاملA New Method for Predicting Well Pattern Connectivity in a Continental Fluvial-delta Reservoir
The features of bad flow unit continuity and multiple layers emphesize the importance of a well pattern design for the development of a fluvial-delta reservoir. It is proposed a method to predict well pattern connectivity (WPC) based on the exploration and evaluation of wells. Moreover, the method helps evaluate the risk of well placement. This study initially establishes the parameters for cha...
متن کاملRock typing and reservoir zonation based on the NMR logging and geological attributes in the mixed carbonate-siliciclastic Asmari Reservoir
Rock typing is known as the best way in heterogeneous reservoirs characterization. The rock typing methods confine to various aspects of the rocks such as multi-scale and multi-modal pore types and size, rock texture, diagenetic modifications and integration of static/dynamic data. Integration of static and dynamic behavior of rocks and their sedimentary features are practiced in this study. Po...
متن کاملIntrinsic plasticity for reservoir learning algorithms
One of the most difficult problems in using dynamic reservoirs like echo state networks for signal processing is the choice of reservoir network parameters like connectivity or spectral radius of the weight matrix. In this article, we investigate the properties of an unsupervised intrinsic plasticity rule for signal specific adaptive shaping of the reservoir, which is local in space and time an...
متن کاملOn the Correlation between Reservoir Metrics and Performance for Time Series Classification under the Influence of Synaptic Plasticity
Reservoir computing provides a simpler paradigm of training recurrent networks by initialising and adapting the recurrent connections separately to a supervised linear readout. This creates a problem, though. As the recurrent weights and topology are now separated from adapting to the task, there is a burden on the reservoir designer to construct an effective network that happens to produce sta...
متن کامل