Analog recurrent neural network simulation, Θ(log2 n) unordered search, and bitonic sort with an optically-inspired model of computation
نویسندگان
چکیده
We prove computability and complexity results for an original model of computation. Our model is inspired by the theory of Fourier optics. We prove our model can simulate analog recurrent neural networks, thus establishing a lower bound on its computational power. We also prove some computational complexity results for searching and sorting algorithms expressed with our model.
منابع مشابه
An optical model of computation
We prove computability and complexity results for an original model of computation called the continuous space machine. Our model is inspired by the theory of Fourier optics.We prove our model can simulate analog recurrent neural networks, thus establishing a lower bound on its computational power. We also define a (log2 n) unordered search algorithm with our model. © 2004 Elsevier B.V. All rig...
متن کاملDeep Neural Architectures for Algorithms and Sequential Data
The first part of the dissertation describes two deep neural architectures with external memories: Neural Random-Access Machine (NRAM) and Hierarchical Attentive Memory (HAM). The NRAM architecture is inspired by Neural Turing Machines, but the crucial difference is that it can manipulate and dereference pointers to its randomaccess memory. This allows it to learn concepts that require pointers...
متن کاملA New Recurrent Fuzzy Neural Network Controller Design for Speed and Exhaust Temperature of a Gas Turbine Power Plant
In this paper, a recurrent fuzzy-neural network (RFNN) controller with neural network identifier in direct control model is designed to control the speed and exhaust temperature of the gas turbine in a combined cycle power plant. Since the turbine operation in combined cycle unit is considered, speed and exhaust temperature of the gas turbine should be simultaneously controlled by fuel command ...
متن کاملA Recurrent Neural Network to Identify Efficient Decision Making Units in Data Envelopment Analysis
In this paper we present a recurrent neural network model to recognize efficient Decision Making Units(DMUs) in Data Envelopment Analysis(DEA). The proposed neural network model is derived from an unconstrained minimization problem. In theoretical aspect, it is shown that the proposed neural network is stable in the sense of lyapunov and globally convergent. The proposed model has a single-laye...
متن کاملAn efficient one-layer recurrent neural network for solving a class of nonsmooth optimization problems
Constrained optimization problems have a wide range of applications in science, economics, and engineering. In this paper, a neural network model is proposed to solve a class of nonsmooth constrained optimization problems with a nonsmooth convex objective function subject to nonlinear inequality and affine equality constraints. It is a one-layer non-penalty recurrent neural network based on the...
متن کامل