Reservoir computing for static pattern recognition
نویسندگان
چکیده
This paper introduces reservoir computing for static pattern recognition. Reservoir computing networks are neural networks with a sparsely connected recurrent hidden layer (or reservoir) of neurons. The weights from the inputs to the reservoir and the reservoir weights are randomly selected. The weights of the second layer are determined with a linear partial least squares solver. The outputs of the reservoir layer can be considered to be an unsupervised data transformation. This stage has a brain-like plausibility. This paper shows that by letting the dynamics of the reservoir evolve to a stable solution, and then applying a sigmoid transfer function, reservoir computing can be applied as a robust and highly accurate pattern classifier. Reservoir computing is applied to 16 difficult multi-class classification benchmark cases, and compared with the best results of state-of the art neural network classification methods with entropic error criteria.
منابع مشابه
Reservoir Computing using Stochastic p-Bits
We present a general hardware framework for building networks that directly implement Reservoir Computing, a popular software method for implementing and training Recurrent Neural Networks and are particularly suited for temporal inferencing and pattern recognition. We provide a specific example of a candidate hardware unit based on a combination of soft-magnets, spin-orbit materials and CMOS t...
متن کاملStability and Topology in Reservoir Computing
Recently Jaeger and others have put forth the paradigm of "reservoir computing" as a way of computing with highly recurrent neural networks. This reservoir is a collection of neurons randomly connected with each other of fixed weights. Amongst other things, it has been shown to be effective in temporal pattern recognition; and has been held as a model appropriate to explain how certain aspects ...
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 کاملReservoir Computing with Stochastic Bitstream Neurons
Reservoir Computing (RC) [6], [5], [9] is a computational framework with powerful properties and several interesting advantages compared to conventional techniques for pattern recognition. It consists essentially of two parts: a recurrently connected network of simple interacting nodes (the reservoir), and a readout function that observes the reservoir and computes the actual output of the syst...
متن کاملPhotonic Reservoir Computing with Coupled Semiconductor Optical Amplifiers
We propose photonic reservoir computing as a new approach to optical signal processing and it can be used to handle for example large scale pattern recognition. Reservoir computing is a new learning method from the field of machine learning. This has already led to impressive results in software but integrated photonics with its large bandwidth and fast nonlinear effects would be a high-perform...
متن کامل