High Speed Optical Higher Order Neural Networks for Discovering Data Trends and Patterns in Very Large Databases

This chapter describes the progress in using optical technology to construct high-speed artificial higher order neural network systems. The chapter reviews how optical technology can speed up searches within large databases in order to identify relationships and dependencies between individual data records, such as financial or business time-series, as well as trends and relationships within them. Two distinct approaches in which optics may be used are reviewed. In the first approach, the chapter reviews current research replacing copper connections in a conventional data storage system, such as a several terabyte RAID array of magnetic hard discs, by optical waveguides to achieve very high data rates with low crosstalk interference. In the second approach, the chapter reviews how high speed optical correlators with feedback can be used to realize artificial higher order neural networks using Fourier Transform free space optics and holographic database storage.

Higher Order Neural Networks in a Unified Learning Scheme

ICANN ’93 ◽

10.1007/978-1-4471-2063-6_187 ◽

1993 ◽

pp. 679-682

Author(s):

Arnd Bischoff ◽

Bernd Schürmann

Keyword(s):

Neural Networks ◽

Higher Order ◽

Learning Scheme ◽

Towards Designing and Performance Analysis of Evolving Higher Order Neural Networks for Modeling and Forecasting Exchange Rate Time Series Data

Proceedings of ICETIT 2019 - Lecture Notes in Electrical Engineering ◽

10.1007/978-3-030-30577-2_22 ◽

2019 ◽

pp. 258-268

Author(s):

Kishore Kumar Sahu ◽

Sarat Chandra Nayak ◽

Himansu Sekhar Behera

Keyword(s):

Neural Networks ◽

Time Series ◽

Exchange Rate ◽

Performance Analysis ◽

Time Series Data ◽

Higher Order ◽

Series Data ◽

Modeling And Forecasting ◽

And Performance

Higher Order Neural Networks for Satellite Weather Prediction

Studies in Fuzziness and Soft Computing - Applied Intelligent Systems ◽

10.1007/978-3-540-39972-8_2 ◽

2004 ◽

pp. 17-57 ◽

Cited By ~ 12

Author(s):

Ming Zhang ◽

John Fulcher

Keyword(s):

Neural Networks ◽

Weather Prediction ◽

Higher Order ◽

Advances in Soft Computing - The Sixth International Symposium on Neural Networks (ISNN 2009) ◽

Adaptive Higher Order Neural Networks for Effective Data Mining

10.1007/978-3-642-01216-7_18 ◽

2009 ◽

pp. 165-173 ◽

Cited By ~ 1

Author(s):

Shuxiang Xu ◽

Ling Chen

Keyword(s):

Data Mining ◽

Neural Networks ◽

Higher Order ◽

Stock Price Forecasting using Higher Order Neural Networks

IASTED Technology Conferences / 696:MS / 697:CA / 698: WC / 699: EME / 700: SOE ◽

10.2316/p.2010.696-107 ◽

2010 ◽

Author(s):

A.M. Kimiagari ◽

M. Keyvanloo ◽

M. Fallahnezhad ◽

M.H. Moradi ◽

A.B. Farimani

Keyword(s):

Neural Networks ◽

Stock Price ◽

Higher Order ◽

Price Forecasting ◽

Stock Price Forecasting ◽

Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing 2011 - Studies in Computational Intelligence ◽

Sin and Sigmoid Higher Order Neural Networks for Data Simulations and Predictions

10.1007/978-3-642-22288-7_4 ◽

2011 ◽

pp. 41-54

Author(s):

Ming Zhang

Keyword(s):

Neural Networks ◽

Higher Order ◽

On Some Dynamical Properties of Randomly Connected Higher Order Neural Networks

Artificial Higher Order Neural Networks for Modeling and Simulation ◽

10.4018/978-1-4666-2175-6.ch016 ◽

2013 ◽

pp. 333-363

Author(s):

Hiromi Miyajima ◽

Noritaka Shigei ◽

Shuji Yatsuki

Keyword(s):

Neural Networks ◽

Statistical Method ◽

Complex Dynamics ◽

Higher Order ◽

State Model ◽

Macroscopic Properties ◽

Dynamical Properties ◽

Model C ◽

Convenient Model

This chapter presents macroscopic properties of higher order neural networks. Randomly connected Neural Networks (RNNs) are known as a convenient model to investigate the macroscopic properties of neural networks. They are investigated by using the statistical method of neuro-dynamics. By applying the approach to higher order neural networks, macroscopic properties of them are made clear. The approach establishes: (a) there are differences between stability of RNNs and Randomly connected Higher Order Neural Networks (RHONNs) in the cases of the digital state -model and the analog state model; (b) there is no difference between stability of RNNs and RHONNs in the cases of the digital state -model and the analog state -model; (c) with neural networks with oscillation, there are large differences between RNNs and RHONNs in the cases of the digital state -model and the analog state -model, that is, there exists complex dynamics in each model for ; (d) behavior of groups composed of RHONNs are represented as a combination of the behavior of each RHONN.

Fundamentals of Higher Order Neural Networks for Modeling and Simulation

Artificial Higher Order Neural Networks for Modeling and Simulation ◽

10.4018/978-1-4666-2175-6.ch006 ◽

2013 ◽

pp. 103-133 ◽

Cited By ~ 13

Author(s):

Madan M. Gupta ◽

Ivo Bukovsky ◽

Noriyasu Homma ◽

Ashu M. G. Solo ◽

Zeng-Guang Hou

Keyword(s):

Neural Networks ◽

Modeling And Simulation ◽

Learning Algorithm ◽

Nonlinear Approximation ◽

Higher Order ◽

High Dynamic ◽

Input Variables ◽

Continuous Dynamic

In this chapter, the authors provide fundamental principles of Higher Order Neural Units (HONUs) and Higher Order Neural Networks (HONNs) for modeling and simulation. An essential core of HONNs can be found in higher order weighted combinations or correlations between the input variables and HONU. Except for the high quality of nonlinear approximation of static HONUs, the capability of dynamic HONUs for the modeling of dynamic systems is shown and compared to conventional recurrent neural networks when a practical learning algorithm is used. In addition, the potential of continuous dynamic HONUs to approximate high dynamic order systems is discussed, as adaptable time delays can be implemented. By using some typical examples, this chapter describes how and why higher order combinations or correlations can be effective for modeling of systems.

A New Topology for Artificial Higher Order Neural Networks

Artificial Higher Order Neural Networks for Economics and Business ◽

10.4018/978-1-59904-897-0.ch019 ◽

2009 ◽

pp. 430-441 ◽

Cited By ~ 2

Author(s):

Zhao Lu ◽

Leang-san Shieh ◽

Guanrong Chen

Keyword(s):

Neural Networks ◽

Network Performance ◽

System Modeling ◽

Higher Order ◽

Polynomial Kernel ◽

Support Vector ◽

Risk Minimization ◽

Hidden Layer ◽

Kernel Support Vector Machines

Aiming to develop a systematic approach for optimizing the structure of artificial higher order neural networks (HONN) for system modeling and function approximation, a new HONN topology, namely polynomial kernel networks, is proposed in this chapter. Structurally, the polynomial kernel network can be viewed as a three-layer feedforward neural network with a special polynomial activation function for the nodes in the hidden layer. The new network is equivalent to a HONN; however, due to the underlying connections with polynomial kernel support vector machines, the weights and the structure of the network can be determined simultaneously using structural risk minimization. The advantage of the topology of the polynomial kernel network and the use of a support vector kernel expansion paves the way to represent nonlinear functions or systems, and underpins some advanced analysis of the network performance. In this chapter, from the perspective of network complexity, both quadratic programming and linear programming based training of the polynomial kernel network are investigated.