A New Stochastic Learning Algorithm for Neural Networks
نویسندگان
چکیده
A new stochastic learning algorithm using Gaussian white noise sequence, referred to as Subconscious Noise Reaction (SNR), is proposed for a class of discrete-time neural networks with time-dependent connection weights. Unlike the back-propagation-through-time (BTT) algorithm, SNR does not require the synchronous transmission of information backward along connection weights, while it uses only ubiquitous noise and local signals, which are correlated against a single performance functional, to achieve simple sequential (chronologically ordered) updating of connection weights. The algorithm is derived and analyzed on the basis of a functional derivative formulation of the gradient descent method in conjunction with stochastic ~ensit~ivity analysis techniques using the ~ariationa~l approach.
منابع مشابه
Solving Fuzzy Equations Using Neural Nets with a New Learning Algorithm
Artificial neural networks have the advantages such as learning, adaptation, fault-tolerance, parallelism and generalization. This paper mainly intends to offer a novel method for finding a solution of a fuzzy equation that supposedly has a real solution. For this scope, we applied an architecture of fuzzy neural networks such that the corresponding connection weights are real numbers. The ...
متن کاملSolving Fuzzy Equations Using Neural Nets with a New Learning Algorithm
Artificial neural networks have the advantages such as learning, adaptation, fault-tolerance, parallelism and generalization. This paper mainly intends to offer a novel method for finding a solution of a fuzzy equation that supposedly has a real solution. For this scope, we applied an architecture of fuzzy neural networks such that the corresponding connection weights are real numbers. The ...
متن کاملUtilizing a new feed-back fuzzy neural network for solving a system of fuzzy equations
This paper intends to offer a new iterative method based on articial neural networks for finding solution of a fuzzy equations system. Our proposed fuzzied neural network is a ve-layer feedback neural network that corresponding connection weights to output layer are fuzzy numbers. This architecture of articial neural networks, can get a real input vector and calculates its corresponding fuzzy o...
متن کاملA Hybrid Optimization Algorithm for Learning Deep Models
Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...
متن کاملA Hybrid Optimization Algorithm for Learning Deep Models
Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...
متن کاملTraining Radial Basis Function Neural Network using Stochastic Fractal Search Algorithm to Classify Sonar Dataset
Radial Basis Function Neural Networks (RBF NNs) are one of the most applicable NNs in the classification of real targets. Despite the use of recursive methods and gradient descent for training RBF NNs, classification improper accuracy, failing to local minimum and low-convergence speed are defects of this type of network. In order to overcome these defects, heuristic and meta-heuristic algorith...
متن کامل