Neural Network Parallel Computing

Takefuji, Yoshiyasu

doi:10.1007/978-1-4615-3642-0

Cited by 149 publications

(56 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results we obtained are same as predicted by Takefuji [25], but our machine learning algorithm predicted the structure in lesser time since the algorithm we used is quadratic in nature. Nevertheless our system finds out the optimal secondary structure by using statistical methods.…”

Section: Johnson Unbounded 252supporting

confidence: 61%

Secondary Structure Prediction of RNA using Machine Learning Method

Qasim¹,

Kauser²,

Jilani³

2010

IJCA

View full text Add to dashboard Cite

Ribonucleic Acid (RNA) plays a vital role in the transcription process. Since the information stored in DNA is converted into sequences of a chemical compounds named amino acids through mRNA in order to produce the ultimate gene product i.e., protein.The importance of RNA in the transcription process gives a better justification to analyze it. RNA cannot exist stably in its primary structure, thus, to attain a stable structure, it folds back on itself to form secondary structure (2o RNA) and further folding of RNA nucleotides gives rise to the tertiary structure (3o RNA). In this paper, a new model using neural network for RNA secondary structure prediction is proposed. Our computational model predicts multiple secondary structures of a single RNA by applying a parallel algorithm for finding near maximum independent set in the circle graph proposed by Takefuji Y. et al (1990). Based on frequency density analysis of the predicted RNA secondary structures, we proposed an optimized secondary structure of RNA among all the possibilities using statistical probability distributions. The paper concludes by discussing the nature and behavior of 2o RNA predicted by our method and a comparison with the results of other researchers. We have shown that the proposed model has better accuracy as compared to the other researches.

show abstract

Section: Johnson Unbounded 252supporting

confidence: 61%

Secondary Structure Prediction of RNA using Machine Learning Method

Qasim¹,

Kauser²,

Jilani³

2010

IJCA

View full text Add to dashboard Cite

show abstract

“…Figure 3 shows how a neuron calculates its activity using the inputs. A neuron in the output layer computes its activity using equations (1) and (2). Here, f(x) is the scaling function which is generally the sigmoid function.…”

Section: Back-propagation Algorithm For Neural Networkmentioning

confidence: 99%

“…rtificial Neural Networks (ANN) [1][2][3][4] have been used for many complex tasks such as stock prediction and nonlinear function approximations. The neural network methodology is free from the algorithmic complexity that is usually associated with these tasks.…”

Section: Introductionmentioning

confidence: 99%

Scalable Massively Parallel Artificial Neural Networks

Long¹,

Gupta

2008

Journal of Aerospace Computing, Information, and Communication

View full text Add to dashboard Cite

There is renewed interest in computational intelligence, due to advances in algorithms, neuroscience, and computer hardware. In addition there is enormous interest in autonomous vehicles (air, ground, and sea) and robotics, which need significant onboard intelligence. Work in this area could not only lead to better understanding of the human brain but also very useful engineering applications. The functioning of the human brain is not well understood, but enormous progress has been made in understanding it and, in particular, the neocortex. There are many reasons to develop models of the brain. Artificial Neural Networks (ANN), one type of model, can be very effective for pattern recognition, function approximation, scientific classification, control, and the analysis of time series data. ANNs often use the back-propagation algorithm for training, and can require large training times especially for large networks, but there are many other types of ANNs. Once the network is trained for a particular problem, however, it can produce results in a very short time. Parallelization of ANNs could drastically reduce the training time. An object-oriented, massively-parallel ANN (Artificial Neural Network) software package SPANN (Scalable Parallel Artificial Neural Network) has been developed and is described here. MPI was used to parallelize the C++ code. Only the neurons on the edges of the domains were involved in communication, in order to reduce the communication costs and maintain scalability. The back-propagation algorithm was used to train the network. In preliminary tests, the software was used to identify character sets. The code correctly identified all the characters when adequate training was used in the network. The code was run on up to 500 Intel Itanium processors with 25,000 neurons and more than 2 billion neuron weights. Various comparisons in training time, forward propagation time, and error reduction were also made.

show abstract

“…For a given neural system, both the structure design and access time needed to solve the problem are two most important performance measures [13], [25]- [30]. In this section, we will analyze these measures for our pipelined neural architecture, where parallel processing stage defined in Fig.…”

Section: Structure Analysismentioning

confidence: 99%

“…The size of the window can be selected directly from the relation [see Fig. 14(b)], which leads to (30) Hence, the choice of the window size for type 2 is (31)…”

Section: Letmentioning

confidence: 99%

Parallel system design for time-delay neural networks

Zhang

Pal

2000

IEEE Trans. Syst., Man, Cybern. C

View full text Add to dashboard Cite

Abstract-In this paper, we develop a parallel structure for the time-delay neural network used in some speech recognition applications. The effectiveness of the design is illustrated by 1) extracting a window computing model from the time-delay neural systems; 2) building its pipelined architecture with parallel or serial processing stages; and 3) applying this parallel window computing to some typical speech recognition systems. An analysis of the complexity of the proposed design shows a greatly reduced complexity while maintaining a high throughput rate.

show abstract

Neural Network Parallel Computing

Cited by 149 publications

References 84 publications

Secondary Structure Prediction of RNA using Machine Learning Method

Secondary Structure Prediction of RNA using Machine Learning Method

Scalable Massively Parallel Artificial Neural Networks

Parallel system design for time-delay neural networks

Contact Info

Product

Resources

About