Locally Connected Recurrent Networks
نویسنده
چکیده
The fully connected recurrent network (FRN) using the on-line training method, Real Time Recurrent Learning (RTRL), is computationally expensive. It has a computational complexity of O(N 4) and storage complexity of O(N 3), where N is the number of non-input units. We have devised a locally connected recurrent model which has a much lower complexity in both computational time and storage space. The ring-structure recurrent network (RRN), the simplest kind of the locally connected has the corresponding complexity of O(mn+np) and O(np) respectively, where p, n and m are the number of input, hidden and output units respectively. We compare the performance between RRN and FRN in sequence recognition and time series prediction. We tested the networks' ability in temporal memorizing power and time warpping ability in the sequence recognition task. In the time series prediction task, we used both networks to train and predict three series; a periodic series with white noise, a deter-ministic chaotic series and the sunspots data. Both tasks show that RRN needs a much shorter training time and the performance of RRN is comparable to that of FRN.
منابع مشابه
Fault Detection and Location in DC Microgrids by Recurrent Neural Networks and Decision Tree Classifier
Microgrids have played an important role in distribution networks during recent years. DC microgrids are very popular among researchers because of their benefits. Protection is one of the significant challenges in the way of microgrids progress. As a result, in this paper, a fault detection and location scheme for DC microgrids is proposed. Due to advances in Artificial Intelligence (AI) and s...
متن کاملConnection Reduction of the Recurrent Networks
There are many variations on the topology of recurrent networks. Models with fully-connected recurrent weights may not be superior to those models with sparsely connected recurrent weights in terms of capacity, time for training and generalization ability. In this paper, we show that the fully-connected recurrent networks can be reduced to functionally equivalent partially-connected recurrent n...
متن کاملA Speech Recognizer with Low Complexity Based on Rnn
Speech recognition systems (SRS) designed for applications in low cost products like telephones or in systems with energetic constraints like autonomous vehicles are faced with the demand for solutions with low complexity. A small vocabulary consisting of a few command words and the digits is suucient for most of the applications but has to be recognized robustly. Here we report about investiga...
متن کاملUniform connectedness and uniform local connectedness for lattice-valued uniform convergence spaces
We apply Preuss' concept of $mbbe$-connectedness to the categories of lattice-valued uniform convergence spaces and of lattice-valued uniform spaces. A space is uniformly $mbbe$-connected if the only uniformly continuous mappings from the space to a space in the class $mbbe$ are the constant mappings. We develop the basic theory for $mbbe$-connected sets, including the product theorem. Furtherm...
متن کامل