Negative initial weights improve learning in recurrent neural networks
نویسندگان
چکیده
منابع مشابه
An `introspective' Network That Can Learn to Run Its Own Weight
Usually weight changes in neural networks are exclusively caused by some hard-wired learning algorithm with many speciic limitations. I show that it is in principle possible to let the network run and improve its own weight change algorithm (without sig-niicant theoretical limits). I derive an initial gradient-based supervised sequence learning algorithm for anìn-trospective' recurrent network ...
متن کاملCystoscopic Image Classification Based on Combining MLP and GA
In the past three decades, the use of smart methods in medical diagnostic systems has attracted the attention of many researchers. However, no smart activity has been provided in the field of medical image processing for diagnosis of bladder cancer through cystoscopy images despite the high prevalence in the world. In this paper, a multilayer neural network was applied to clas...
متن کاملLearning the initial state of a second - order recurrentneural network during regular - language inferenceMikel
Recent work has shown that second-order recurrent neural networks (2ORNNs) may be used to infer regular languages. This letter presents a modiied version of the real-time recurrent learning (RTRL) algorithm used to train 2ORNNs, that learns the initial state in addition to the weights. The results of this modiication, which adds extra ex-ibility at a negligible cost in time complexity, suggest ...
متن کاملOutlier Detection Using Extreme Learning Machines Based on Quantum Fuzzy C-Means
One of the most important concerns of a data miner is always to have accurate and error-free data. Data that does not contain human errors and whose records are full and contain correct data. In this paper, a new learning model based on an extreme learning machine neural network is proposed for outlier detection. The function of neural networks depends on various parameters such as the structur...
متن کاملNumerical solution of fuzzy differential equations under generalized differentiability by fuzzy neural network
In this paper, we interpret a fuzzy differential equation by using the strongly generalized differentiability concept. Utilizing the Generalized characterization Theorem. Then a novel hybrid method based on learning algorithm of fuzzy neural network for the solution of differential equation with fuzzy initial value is presented. Here neural network is considered as a part of large eld called ne...
متن کامل