Test Bed for Multilayered Feed forward Neural Network Architectures as Bidirectional Associative Memory
نویسنده
چکیده
Multilayered feed-forward neural networks are considered universal approximators and hence extensively been used for function approximation. Function approximation is an instance of supervised learning which is one of the most studied topics in machine learning, artificial neural networks, pattern recognition, and statistical curve fitting. Bidirectional associative memory is another class of networks which has been used for approximating various functions. In the present study, an approach for using MLFNN architectures as BAM with BP learning has been proposed and initially been tested on certain functions. The results obtained are analyzed and presented.
منابع مشابه
Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidirectional Associative Memory (BAM) for Function Approximation
Function approximation is to find the underlying relationship from à given finite input-output data. It has numerous applications such as prediction, pattern recognition, data mining and classification etc. Multilayered feed-forward neural networks (MLFNNs) with the use of back propagation algorithm have been extensively used for the purpose of function approximation recently. Another class of ...
متن کاملExploring Optimal Architecture of Multi-layered Feed- forward (MLFNN) as Bidirectional Associative Memory (BAM) for Function Approximation
Function approximation is an instance of supervised learning which is one of the most studied topics in machine learning, artificial neural networks, pattern recognition, and statistical curve fitting. In principle, any of the methods studied in these fields can be used in reinforcement learning. Multi-layered feed-forward neural networks (MLFNN) have been extensively used for the purpose of fu...
متن کاملFramewise phoneme classification with bidirectional LSTM and other neural network architectures
In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, a...
متن کاملTransputer-based Parallel Systems for Performance Evaluation of Bidirectional Associative Memory
In this paper, we discuss parallel implementation of an artificial neural network for pattern d a t i o n , the Bidirectional Associative Memory(BAM). Transputer-based parallel architecture8 like hypercube, mesh and linear array are used to exploit the parallelism in BAM. A comparitive study of utilization and speedup for various architectures is made. Hypercube performs better in terms of util...
متن کاملModeling SMA actuated systems based on Bouc-Wen hysteresis model and feed-forward neural network
Despite the fact that shape-memory alloy (SMA) has several mechanical advantages as it continues being used as an actuator in engineering applications, using it still remains as a challenge since it shows both non-linear and hysteretic behavior. To improve the efficiency of SMA application, it is required to do research not only on modeling it, but also on control hysteresis behavior of these m...
متن کامل